Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.1279. Min Act: -0.1700
Data Index: 8532543 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.1279. Min Act: -0.1700
Data Index: 1023997 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0654. Min Act: -0.1700
Data Index: 3017477 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0341. Min Act: -0.1700
Data Index: 7725559 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0341. Min Act: -0.1700
Data Index: 248260 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0341. Min Act: -0.1700
Data Index: 7229236 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0341. Min Act: -0.1700
Data Index: 7038612 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0341. Min Act: -0.1700
Data Index: 5573780 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0341. Min Act: -0.1700
Data Index: 4038578 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0029. Min Act: -0.1700
Data Index: 1023998 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0029. Min Act: -0.1700
Data Index: 1708621 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0029. Min Act: -0.1700
Data Index: 248263 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9716. Min Act: -0.1700
Data Index: 4500822 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9716. Min Act: -0.1700
Data Index: 3709661 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9716. Min Act: -0.1700
Data Index: 7038614 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9716. Min Act: -0.1700
Data Index: 3228338 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1279. Min Range: -6.1279
Max Act: 6.0029. Min Act: -0.1700
Data Index: 8532551 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9716. Min Act: -0.1700
Data Index: 6243054 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9404. Min Act: -0.1700
Data Index: 1621171 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1279. Min Range: -6.1279
Max Act: 5.9404. Min Act: -0.1700
Data Index: 3528448 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19