Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2553 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0123. Min Range: -6.0123
Max Act: 6.0123. Min Act: -0.1700
Data Index: 2490857 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.8248. Min Act: -0.1700
Data Index: 7843298 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.7310. Min Act: -0.1700
Data Index: 8192263 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.6373. Min Act: -0.1700
Data Index: 3268051 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.6060. Min Act: -0.1700
Data Index: 6420867 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.5435. Min Act: -0.1700
Data Index: 1456016 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.5435. Min Act: -0.1700
Data Index: 5029851 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.4810. Min Act: -0.1700
Data Index: 3472950 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.4498. Min Act: -0.1700
Data Index: 1118649 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.4498. Min Act: -0.1700
Data Index: 4999272 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.4498. Min Act: -0.1700
Data Index: 8270456 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.4498. Min Act: -0.1700
Data Index: 5096934 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.4185. Min Act: -0.1700
Data Index: 8730669 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.3560. Min Act: -0.1700
Data Index: 8290147 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.3560. Min Act: -0.1700
Data Index: 3342720 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.3560. Min Act: -0.1700
Data Index: 6417738 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.3560. Min Act: -0.1700
Data Index: 5608895 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.2935. Min Act: -0.1700
Data Index: 6091441 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.2935. Min Act: -0.1700
Data Index: 36920 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0123. Min Range: -6.0123
Max Act: 5.2935. Min Act: -0.1700
Data Index: 5103461 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #19