Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3707 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.7883. Min Act: -0.1700
Data Index: 8282766 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.5383. Min Act: -0.1700
Data Index: 1283635 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.4133. Min Act: -0.1700
Data Index: 3145717 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.3196. Min Act: -0.1700
Data Index: 7903630 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.2883. Min Act: -0.1700
Data Index: 1517535 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.2571. Min Act: -0.1700
Data Index: 4867604 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1946. Min Act: -0.1700
Data Index: 6684539 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.2258. Min Act: -0.1700
Data Index: 7058564 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.2258. Min Act: -0.1700
Data Index: 4816617 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.2258. Min Act: -0.1700
Data Index: 4816616 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1946. Min Act: -0.1700
Data Index: 4301308 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1946. Min Act: -0.1700
Data Index: 7942451 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.2258. Min Act: -0.1700
Data Index: 2359497 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1946. Min Act: -0.1700
Data Index: 532733 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1633. Min Act: -0.1700
Data Index: 7248453 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1633. Min Act: -0.1700
Data Index: 5398413 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1633. Min Act: -0.1700
Data Index: 3932777 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1633. Min Act: -0.1700
Data Index: 1092981 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1633. Min Act: -0.1700
Data Index: 6106614 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7883. Min Range: -4.7883
Max Act: 4.1946. Min Act: -0.1700
Data Index: 4477639 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19