Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.4177. Min Range: -13.4177
Max Act: 13.4177. Min Act: -0.1700
Data Index: 6893207 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.7927. Min Act: -0.1700
Data Index: 2796945 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.7927. Min Act: -0.1700
Data Index: 5030296 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.6052. Min Act: -0.1700
Data Index: 1050656 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.4177. Min Act: -0.1700
Data Index: 3832807 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.4177. Min Act: -0.1700
Data Index: 2241921 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.4177. Min Act: -0.1700
Data Index: 6250828 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.2927. Min Act: -0.1700
Data Index: 6057415 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.2927. Min Act: -0.1700
Data Index: 3987900 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.2302. Min Act: -0.1700
Data Index: 2494646 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.2302. Min Act: -0.1700
Data Index: 2049444 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.2302. Min Act: -0.1700
Data Index: 5218074 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.1677. Min Act: -0.1700
Data Index: 1369773 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.1677. Min Act: -0.1700
Data Index: 1102910 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.0427. Min Act: -0.1700
Data Index: 8038744 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.1052. Min Act: -0.1700
Data Index: 3820154 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.1052. Min Act: -0.1700
Data Index: 2198736 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.1052. Min Act: -0.1700
Data Index: 7430716 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.1052. Min Act: -0.1700
Data Index: 8457166 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.4177. Min Range: -13.4177
Max Act: 12.0427. Min Act: -0.1700
Data Index: 2502102 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19