Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2708 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1776. Min Range: -7.1776
Max Act: 7.1776. Min Act: -0.1700
Data Index: 1100730 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1776. Min Range: -7.1776
Max Act: 7.0839. Min Act: -0.1700
Data Index: 8387507 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1776. Min Range: -7.1776
Max Act: 7.0526. Min Act: -0.1700
Data Index: 8658906 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.9589. Min Act: -0.1700
Data Index: 7408809 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.7714. Min Act: -0.1700
Data Index: 6724639 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.7401. Min Act: -0.1700
Data Index: 1482919 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.7401. Min Act: -0.1700
Data Index: 6139363 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.7089. Min Act: -0.1700
Data Index: 7533806 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.7089. Min Act: -0.1700
Data Index: 6139160 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.7089. Min Act: -0.1700
Data Index: 7915855 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6464. Min Act: -0.1700
Data Index: 6139158 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6464. Min Act: -0.1700
Data Index: 4328115 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6151. Min Act: -0.1700
Data Index: 5850093 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6151. Min Act: -0.1700
Data Index: 3291384 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.6151. Min Act: -0.1700
Data Index: 4371984 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.5839. Min Act: -0.1700
Data Index: 7924467 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.5839. Min Act: -0.1700
Data Index: 597124 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.5526. Min Act: -0.1700
Data Index: 4267741 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.5214. Min Act: -0.1700
Data Index: 7626961 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1776. Min Range: -7.1776
Max Act: 6.5526. Min Act: -0.1700
Data Index: 824012 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19