Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2667 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.9395. Min Act: -0.1700
Data Index: 7650386 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.8145. Min Act: -0.1700
Data Index: 1675809 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.8145. Min Act: -0.1700
Data Index: 545059 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.7833. Min Act: -0.1700
Data Index: 1071529 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.7208. Min Act: -0.1700
Data Index: 8690940 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6895. Min Act: -0.1700
Data Index: 4282171 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 1954929 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6583. Min Act: -0.1700
Data Index: 1393129 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 1960377 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 840353 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 4745718 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.5958. Min Act: -0.1700
Data Index: 5520495 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6583. Min Act: -0.1700
Data Index: 100213 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 6759660 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 3631920 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 2737439 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.6270. Min Act: -0.1700
Data Index: 6911532 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.5958. Min Act: -0.1700
Data Index: 1998158 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.5958. Min Act: -0.1700
Data Index: 6569026 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9395. Min Range: -4.9395
Max Act: 4.5958. Min Act: -0.1700
Data Index: 7441212 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19