Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2228. Min Range: -6.2228
Max Act: 6.2228. Min Act: -0.1700
Data Index: 7709932 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2228. Min Range: -6.2228
Max Act: 6.1916. Min Act: -0.1700
Data Index: 1206420 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2228. Min Range: -6.2228
Max Act: 6.0978. Min Act: -0.1700
Data Index: 7234730 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2228. Min Range: -6.2228
Max Act: 6.0353. Min Act: -0.1700
Data Index: 4958973 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9728. Min Act: -0.1700
Data Index: 7009212 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2228. Min Range: -6.2228
Max Act: 6.0041. Min Act: -0.1700
Data Index: 2466152 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2228. Min Range: -6.2228
Max Act: 6.0041. Min Act: -0.1700
Data Index: 275362 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9728. Min Act: -0.1700
Data Index: 7027930 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9416. Min Act: -0.1700
Data Index: 6317300 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9416. Min Act: -0.1700
Data Index: 1501634 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9416. Min Act: -0.1700
Data Index: 5769419 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9103. Min Act: -0.1700
Data Index: 1464864 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9103. Min Act: -0.1700
Data Index: 3837340 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.8791. Min Act: -0.1700
Data Index: 3314399 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.8791. Min Act: -0.1700
Data Index: 2993953 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.8478. Min Act: -0.1700
Data Index: 6066449 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.9103. Min Act: -0.1700
Data Index: 5985182 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.8478. Min Act: -0.1700
Data Index: 5437073 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.8166. Min Act: -0.1700
Data Index: 3332346 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2228. Min Range: -6.2228
Max Act: 5.8478. Min Act: -0.1700
Data Index: 623747 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19