Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.9084. Min Act: -0.1700
Data Index: 7684559 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.9084. Min Act: -0.1700
Data Index: 498801 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.8772. Min Act: -0.1700
Data Index: 5590781 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.8772. Min Act: -0.1700
Data Index: 7868667 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.8459. Min Act: -0.1700
Data Index: 7552419 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.8147. Min Act: -0.1700
Data Index: 4210545 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7522. Min Act: -0.1700
Data Index: 2859146 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7522. Min Act: -0.1700
Data Index: 3029370 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 8083268 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 5261475 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 7647610 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 3635617 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 5241174 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 3166843 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 8218940 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.7209. Min Act: -0.1700
Data Index: 1383298 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.6897. Min Act: -0.1700
Data Index: 1134107 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.6897. Min Act: -0.1700
Data Index: 4285882 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.6897. Min Act: -0.1700
Data Index: 6155973 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9084. Min Range: -5.9084
Max Act: 5.6584. Min Act: -0.1700
Data Index: 1416949 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19