Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.9826. Min Act: -0.1700
Data Index: 5010074 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.9201. Min Act: -0.1700
Data Index: 5313622 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.7951. Min Act: -0.1700
Data Index: 8584491 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.7951. Min Act: -0.1700
Data Index: 324803 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.7326. Min Act: -0.1700
Data Index: 1784203 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.7326. Min Act: -0.1700
Data Index: 8659734 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.7013. Min Act: -0.1700
Data Index: 7314005 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.7013. Min Act: -0.1700
Data Index: 3448411 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.6701. Min Act: -0.1700
Data Index: 7493502 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.6388. Min Act: -0.1700
Data Index: 7493911 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.6388. Min Act: -0.1700
Data Index: 2127923 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.6076. Min Act: -0.1700
Data Index: 3968449 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.6076. Min Act: -0.1700
Data Index: 4315643 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.5763. Min Act: -0.1700
Data Index: 2916407 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.5451. Min Act: -0.1700
Data Index: 6418684 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.5451. Min Act: -0.1700
Data Index: 3804296 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.5138. Min Act: -0.1700
Data Index: 3993460 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.5138. Min Act: -0.1700
Data Index: 1238033 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.5138. Min Act: -0.1700
Data Index: 1311587 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9826. Min Range: -5.9826
Max Act: 5.5138. Min Act: -0.1700
Data Index: 261054 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19