Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.9191. Min Act: -0.1700
Data Index: 2618859 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.8565. Min Act: -0.1700
Data Index: 3165312 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.7314. Min Act: -0.1700
Data Index: 4266411 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.7471. Min Act: -0.1700
Data Index: 7092606 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.7158. Min Act: -0.1700
Data Index: 7372038 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.7314. Min Act: -0.1700
Data Index: 6702220 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.7001. Min Act: -0.1700
Data Index: 1598407 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6845. Min Act: -0.1700
Data Index: 5089426 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6689. Min Act: -0.1700
Data Index: 8492943 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6689. Min Act: -0.1700
Data Index: 653630 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6532. Min Act: -0.1700
Data Index: 4908965 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6376. Min Act: -0.1700
Data Index: 2247167 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6063. Min Act: -0.1700
Data Index: 8733138 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6219. Min Act: -0.1700
Data Index: 6027301 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6063. Min Act: -0.1700
Data Index: 5027858 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6219. Min Act: -0.1700
Data Index: 7157186 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.6063. Min Act: -0.1700
Data Index: 856025 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.5906. Min Act: -0.1700
Data Index: 8692098 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.5906. Min Act: -0.1700
Data Index: 4956134 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9191. Min Range: -3.9191
Max Act: 3.5750. Min Act: -0.1700
Data Index: 3909921 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19