Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 8 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4953. Min Act: -0.1700
Data Index: 8654432 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4953. Min Act: -0.1700
Data Index: 7863076 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4640. Min Act: -0.1697
Data Index: 1218917 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4640. Min Act: -0.1700
Data Index: 1926616 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4953. Min Act: -0.1696
Data Index: 7977535 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4640. Min Act: -0.1700
Data Index: 6828165 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4328. Min Act: -0.1700
Data Index: 1558238 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4015. Min Act: -0.1700
Data Index: 1367221 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4640. Min Act: -0.1700
Data Index: 5385254 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4328. Min Act: -0.1699
Data Index: 8250348 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4015. Min Act: -0.1700
Data Index: 7254315 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4015. Min Act: -0.1700
Data Index: 2722718 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4015. Min Act: -0.1700
Data Index: 515303 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.3390. Min Act: -0.1698
Data Index: 2723424 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.4328. Min Act: -0.1700
Data Index: 817184 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.3078. Min Act: -0.1700
Data Index: 2042779 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.3390. Min Act: -0.1700
Data Index: 620824 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.2765. Min Act: -0.1700
Data Index: 5160329 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.3390. Min Act: -0.1700
Data Index: 638896 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4953. Min Range: -5.4953
Max Act: 5.2765. Min Act: -0.1700
Data Index: 4434063 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19