Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3508 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.6428. Min Act: -0.1700
Data Index: 817332 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.5802. Min Act: -0.1700
Data Index: 893439 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.5489. Min Act: -0.1700
Data Index: 5943986 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.5176. Min Act: -0.1700
Data Index: 8152724 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.5019. Min Act: -0.1700
Data Index: 6530750 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4862. Min Act: -0.1700
Data Index: 3895571 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4706. Min Act: -0.1700
Data Index: 983380 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4549. Min Act: -0.1700
Data Index: 7728197 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4549. Min Act: -0.1700
Data Index: 1857163 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4549. Min Act: -0.1700
Data Index: 7589484 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4549. Min Act: -0.1700
Data Index: 887786 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4392. Min Act: -0.1700
Data Index: 680796 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4392. Min Act: -0.1700
Data Index: 7994234 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4236. Min Act: -0.1700
Data Index: 3866145 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4236. Min Act: -0.1700
Data Index: 1331428 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4079. Min Act: -0.1700
Data Index: 5913104 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4079. Min Act: -0.1700
Data Index: 8022018 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.3922. Min Act: -0.1700
Data Index: 1526628 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.3765. Min Act: -0.1700
Data Index: 7106929 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6428. Min Range: -3.6428
Max Act: 3.4079. Min Act: -0.1700
Data Index: 7668112 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19