Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2882 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.8834. Min Act: -0.1700
Data Index: 3373221 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.8834. Min Act: -0.1700
Data Index: 8633250 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.6334. Min Act: -0.1700
Data Index: 1073664 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.4771. Min Act: -0.1700
Data Index: 8383741 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.4459. Min Act: -0.1700
Data Index: 5455537 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.2271. Min Act: -0.1700
Data Index: 6918448 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.1646. Min Act: -0.1700
Data Index: 5221770 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.1334. Min Act: -0.1700
Data Index: 6847269 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8834. Min Range: -7.8834
Max Act: 7.1021. Min Act: -0.1700
Data Index: 3603589 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.8209. Min Act: -0.1700
Data Index: 3376928 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.7896. Min Act: -0.1700
Data Index: 6707985 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.7584. Min Act: -0.1700
Data Index: 3735729 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.6959. Min Act: -0.1700
Data Index: 252761 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.6959. Min Act: -0.1700
Data Index: 38608 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.6646. Min Act: -0.1700
Data Index: 2239360 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.6334. Min Act: -0.1700
Data Index: 6992765 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.6021. Min Act: -0.1700
Data Index: 8371070 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.5709. Min Act: -0.1700
Data Index: 8660725 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.5709. Min Act: -0.1700
Data Index: 20217 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8834. Min Range: -7.8834
Max Act: 6.5084. Min Act: -0.1700
Data Index: 3346592 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19