Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5019 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6205. Min Range: -10.6205
Max Act: 10.6205. Min Act: -0.1700
Data Index: 3686806 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.8705. Min Act: -0.1700
Data Index: 8599351 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.8080. Min Act: -0.1700
Data Index: 4884546 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.7455. Min Act: -0.1700
Data Index: 1981903 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.7455. Min Act: -0.1700
Data Index: 7800706 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.6830. Min Act: -0.1700
Data Index: 2383132 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.6830. Min Act: -0.1700
Data Index: 1662656 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.6830. Min Act: -0.1700
Data Index: 1205122 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.6205. Min Act: -0.1700
Data Index: 1617566 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.5580. Min Act: -0.1700
Data Index: 8291506 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.5580. Min Act: -0.1700
Data Index: 5604053 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.5580. Min Act: -0.1700
Data Index: 5097074 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.5580. Min Act: -0.1700
Data Index: 3868328 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.4955. Min Act: -0.1700
Data Index: 5772717 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.5580. Min Act: -0.1700
Data Index: 2780099 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.4955. Min Act: -0.1700
Data Index: 6050119 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.4330. Min Act: -0.1700
Data Index: 4503770 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.4330. Min Act: -0.1700
Data Index: 6752248 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.4330. Min Act: -0.1700
Data Index: 6459909 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6205. Min Range: -10.6205
Max Act: 9.4330. Min Act: -0.1700
Data Index: 7452937 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19