Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.9067. Min Act: -0.1700
Data Index: 7669674 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.8442. Min Act: -0.1700
Data Index: 3403808 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.7192. Min Act: -0.1700
Data Index: 3135638 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.6567. Min Act: -0.1700
Data Index: 6805939 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5942. Min Act: -0.1700
Data Index: 4136668 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5942. Min Act: -0.1700
Data Index: 3883339 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5317. Min Act: -0.1700
Data Index: 1658453 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5317. Min Act: -0.1700
Data Index: 2351145 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5317. Min Act: -0.1700
Data Index: 1455097 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5317. Min Act: -0.1700
Data Index: 3557689 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5005. Min Act: -0.1700
Data Index: 1378063 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.5005. Min Act: -0.1700
Data Index: 5303591 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.4380. Min Act: -0.1700
Data Index: 2915585 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.4380. Min Act: -0.1700
Data Index: 1370954 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.4067. Min Act: -0.1700
Data Index: 6531595 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.4067. Min Act: -0.1700
Data Index: 8477416 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.4067. Min Act: -0.1700
Data Index: 8622380 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.3755. Min Act: -0.1700
Data Index: 872489 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.3755. Min Act: -0.1700
Data Index: 1424595 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.3755. Min Act: -0.1700
Data Index: 4951400 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19