Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.3785. Min Range: -10.3785
Max Act: 10.3785. Min Act: -0.1700
Data Index: 542831 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3785. Min Range: -10.3785
Max Act: 10.1910. Min Act: -0.1700
Data Index: 8370609 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3785. Min Range: -10.3785
Max Act: 10.1285. Min Act: -0.1700
Data Index: 3376954 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3785. Min Range: -10.3785
Max Act: 10.1285. Min Act: -0.1700
Data Index: 2909237 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.9410. Min Act: -0.1700
Data Index: 6123602 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3785. Min Range: -10.3785
Max Act: 10.0035. Min Act: -0.1700
Data Index: 4958428 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.8785. Min Act: -0.1700
Data Index: 2909239 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6910. Min Act: -0.1700
Data Index: 5155579 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6910. Min Act: -0.1700
Data Index: 2909235 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6910. Min Act: -0.1700
Data Index: 4030745 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.7535. Min Act: -0.1700
Data Index: 1403998 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6910. Min Act: -0.1700
Data Index: 8267356 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6910. Min Act: -0.1700
Data Index: 8114960 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6285. Min Act: -0.1700
Data Index: 5236664 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6910. Min Act: -0.1700
Data Index: 1936488 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6285. Min Act: -0.1700
Data Index: 7049498 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.5660. Min Act: -0.1700
Data Index: 1734161 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6285. Min Act: -0.1700
Data Index: 4554705 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.5035. Min Act: -0.1700
Data Index: 4700823 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3785. Min Range: -10.3785
Max Act: 9.6285. Min Act: -0.1700
Data Index: 4568219 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19