Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.4228. Min Act: -0.1700
Data Index: 3065951 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.3603. Min Act: -0.1700
Data Index: 3324464 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.2666. Min Act: -0.1700
Data Index: 966085 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.1728. Min Act: -0.1700
Data Index: 2463585 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.1416. Min Act: -0.1700
Data Index: 3088363 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.0478. Min Act: -0.1700
Data Index: 7817927 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.0791. Min Act: -0.1700
Data Index: 4419520 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4228. Min Range: -7.4228
Max Act: 7.0166. Min Act: -0.1700
Data Index: 67554 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.9541. Min Act: -0.1700
Data Index: 5690255 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.9541. Min Act: -0.1700
Data Index: 8422858 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.8603. Min Act: -0.1700
Data Index: 1847738 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.8916. Min Act: -0.1700
Data Index: 606361 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.8603. Min Act: -0.1700
Data Index: 8574610 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.8291. Min Act: -0.1700
Data Index: 3067112 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.8291. Min Act: -0.1700
Data Index: 1574289 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.8291. Min Act: -0.1700
Data Index: 5234802 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.7353. Min Act: -0.1700
Data Index: 545382 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.7978. Min Act: -0.1700
Data Index: 2117686 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.7666. Min Act: -0.1700
Data Index: 8628799 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4228. Min Range: -7.4228
Max Act: 6.7353. Min Act: -0.1700
Data Index: 3595147 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19