Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1004 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 11.1443. Min Range: -11.1443
Max Act: 11.0818. Min Act: -0.1700
Data Index: 121578 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.9568. Min Act: -0.1700
Data Index: 7414758 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.6443. Min Act: -0.1700
Data Index: 8146930 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.7693. Min Act: -0.1700
Data Index: 5224369 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.7693. Min Act: -0.1700
Data Index: 3537079 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.4568. Min Act: -0.1700
Data Index: 174665 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.2068. Min Act: -0.1700
Data Index: 6587665 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.7068. Min Act: -0.1700
Data Index: 7605247 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.4568. Min Act: -0.1700
Data Index: 3083731 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.8943. Min Act: -0.1700
Data Index: 7092413 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.9568. Min Act: -0.1700
Data Index: 5954336 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1443. Min Range: -11.1443
Max Act: 11.1443. Min Act: -0.1700
Data Index: 3498493 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.8318. Min Act: -0.1700
Data Index: 3275264 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.3318. Min Act: -0.1700
Data Index: 5925137 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.6443. Min Act: -0.1700
Data Index: 6917182 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1443. Min Range: -11.1443
Max Act: 8.5193. Min Act: -0.1700
Data Index: 4305318 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1443. Min Range: -11.1443
Max Act: 10.0193. Min Act: -0.1700
Data Index: 8491806 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.9568. Min Act: -0.1700
Data Index: 5406696 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.8318. Min Act: -0.1700
Data Index: 6331498 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1443. Min Range: -11.1443
Max Act: 9.7068. Min Act: -0.1700
Data Index: 2865972 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19