Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.4252. Min Act: -0.1700
Data Index: 6546792 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.2377. Min Act: -0.1700
Data Index: 4094529 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.2064. Min Act: -0.1700
Data Index: 8268879 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.1439. Min Act: -0.1700
Data Index: 3745291 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.1752. Min Act: -0.1700
Data Index: 8252625 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.1752. Min Act: -0.1700
Data Index: 1874187 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.0814. Min Act: -0.1700
Data Index: 2262583 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.0189. Min Act: -0.1700
Data Index: 87748 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.9877. Min Act: -0.1700
Data Index: 303578 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4252. Min Range: -6.4252
Max Act: 6.0502. Min Act: -0.1700
Data Index: 2002708 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.9877. Min Act: -0.1700
Data Index: 1237514 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.9564. Min Act: -0.1700
Data Index: 5827390 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8939. Min Act: -0.1700
Data Index: 2577260 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8627. Min Act: -0.1700
Data Index: 7830748 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8627. Min Act: -0.1700
Data Index: 144769 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8314. Min Act: -0.1700
Data Index: 2724300 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8314. Min Act: -0.1700
Data Index: 5734438 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8627. Min Act: -0.1700
Data Index: 6121837 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8314. Min Act: -0.1700
Data Index: 3269857 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4252. Min Range: -6.4252
Max Act: 5.8002. Min Act: -0.1700
Data Index: 4280596 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19