Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5800 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.1664. Min Act: -0.1700
Data Index: 6193835 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.1664. Min Act: -0.1700
Data Index: 6212910 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.1352. Min Act: -0.1700
Data Index: 4956632 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.1039. Min Act: -0.1700
Data Index: 1989056 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0727. Min Act: -0.1700
Data Index: 4360687 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0727. Min Act: -0.1700
Data Index: 8381620 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0727. Min Act: -0.1700
Data Index: 7867388 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0727. Min Act: -0.1700
Data Index: 3794522 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 520035 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 2107723 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 2251295 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 5378603 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 4406831 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 6377997 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 2540854 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 2763861 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 82082 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 1740326 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 4989833 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1664. Min Range: -5.1664
Max Act: 5.0414. Min Act: -0.1700
Data Index: 7592415 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19