Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1204 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.9191. Min Act: -0.1700
Data Index: 8463750 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.7316. Min Act: -0.1700
Data Index: 2450737 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.7003. Min Act: -0.1700
Data Index: 3104094 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.7003. Min Act: -0.1700
Data Index: 2409214 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.7003. Min Act: -0.1700
Data Index: 4560844 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.6691. Min Act: -0.1700
Data Index: 7851589 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.6066. Min Act: -0.1700
Data Index: 8543073 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.6066. Min Act: -0.1700
Data Index: 489898 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.5753. Min Act: -0.1700
Data Index: 5527035 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.5441. Min Act: -0.1700
Data Index: 8543072 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.4816. Min Act: -0.1700
Data Index: 2776800 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.4503. Min Act: -0.1700
Data Index: 4533739 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.4816. Min Act: -0.1700
Data Index: 3551108 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.4191. Min Act: -0.1700
Data Index: 1255169 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.4503. Min Act: -0.1700
Data Index: 2974321 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.4191. Min Act: -0.1700
Data Index: 1255170 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.3878. Min Act: -0.1700
Data Index: 6427266 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.3878. Min Act: -0.1700
Data Index: 6552127 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.3878. Min Act: -0.1700
Data Index: 6672141 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9191. Min Range: -5.9191
Max Act: 5.3878. Min Act: -0.1700
Data Index: 4683002 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19