Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1440 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.2285. Min Range: -11.2285
Max Act: 11.2285. Min Act: -0.1700
Data Index: 1967106 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2285. Min Range: -11.2285
Max Act: 11.0410. Min Act: -0.1700
Data Index: 8235740 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2285. Min Range: -11.2285
Max Act: 11.1035. Min Act: -0.1700
Data Index: 1851881 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2285. Min Range: -11.2285
Max Act: 11.1035. Min Act: -0.1700
Data Index: 6608207 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.9785. Min Act: -0.1700
Data Index: 5729106 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.9785. Min Act: -0.1700
Data Index: 3115044 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.8535. Min Act: -0.1700
Data Index: 8830239 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.7910. Min Act: -0.1700
Data Index: 1313830 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.7285. Min Act: -0.1700
Data Index: 4563098 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.7285. Min Act: -0.1700
Data Index: 179265 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.7910. Min Act: -0.1700
Data Index: 8314425 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.7285. Min Act: -0.1700
Data Index: 8119968 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.6660. Min Act: -0.1700
Data Index: 3948225 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.7285. Min Act: -0.1700
Data Index: 6728530 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.6660. Min Act: -0.1700
Data Index: 8702821 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.6660. Min Act: -0.1700
Data Index: 2216404 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.7285. Min Act: -0.1700
Data Index: 4642231 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.6035. Min Act: -0.1700
Data Index: 5353142 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.6035. Min Act: -0.1700
Data Index: 7471396 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2285. Min Range: -11.2285
Max Act: 10.6035. Min Act: -0.1700
Data Index: 4229149 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19