Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.7129. Min Act: -0.1700
Data Index: 2185062 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.6973. Min Act: -0.1700
Data Index: 4057844 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.6660. Min Act: -0.1700
Data Index: 7543507 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.6347. Min Act: -0.1700
Data Index: 3010551 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5721. Min Act: -0.1700
Data Index: 5726621 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5878. Min Act: -0.1700
Data Index: 268991 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.6034. Min Act: -0.1700
Data Index: 427282 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5721. Min Act: -0.1700
Data Index: 8384517 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5408. Min Act: -0.1700
Data Index: 3314502 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5565. Min Act: -0.1700
Data Index: 3338336 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5565. Min Act: -0.1700
Data Index: 6579637 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5565. Min Act: -0.1700
Data Index: 3071301 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5408. Min Act: -0.1700
Data Index: 7867404 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5408. Min Act: -0.1700
Data Index: 6497391 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5251. Min Act: -0.1700
Data Index: 5824901 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5251. Min Act: -0.1700
Data Index: 4122318 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5095. Min Act: -0.1700
Data Index: 7749217 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5095. Min Act: -0.1700
Data Index: 1402774 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.5095. Min Act: -0.1700
Data Index: 6470068 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7129. Min Range: -3.7129
Max Act: 3.4782. Min Act: -0.1700
Data Index: 351132 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #19