Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.5207. Min Act: -0.1700
Data Index: 5884656 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.4582. Min Act: -0.1700
Data Index: 5884662 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.4269. Min Act: -0.1700
Data Index: 3316322 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.3957. Min Act: -0.1700
Data Index: 3040274 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.3644. Min Act: -0.1700
Data Index: 3218566 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.3332. Min Act: -0.1700
Data Index: 1928040 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.3019. Min Act: -0.1700
Data Index: 3415900 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2707. Min Act: -0.1700
Data Index: 206234 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2707. Min Act: -0.1700
Data Index: 4828039 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2707. Min Act: -0.1700
Data Index: 3728044 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2394. Min Act: -0.1700
Data Index: 5884661 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2394. Min Act: -0.1700
Data Index: 392954 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2394. Min Act: -0.1700
Data Index: 232195 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2394. Min Act: -0.1700
Data Index: 5884664 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2707. Min Act: -0.1700
Data Index: 3917353 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.2394. Min Act: -0.1700
Data Index: 5933305 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.1769. Min Act: -0.1700
Data Index: 7018608 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.1769. Min Act: -0.1700
Data Index: 3316323 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.1769. Min Act: -0.1700
Data Index: 384953 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5207. Min Range: -4.5207
Max Act: 4.1456. Min Act: -0.1700
Data Index: 335176 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #19