Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4334 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.8927. Min Act: -0.1700
Data Index: 3438221 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.8302. Min Act: -0.1700
Data Index: 5686789 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.7052. Min Act: -0.1700
Data Index: 3842770 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.7052. Min Act: -0.1700
Data Index: 415646 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.7677. Min Act: -0.1700
Data Index: 4357043 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.7677. Min Act: -0.1700
Data Index: 2291091 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.7052. Min Act: -0.1700
Data Index: 8755746 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.6427. Min Act: -0.1700
Data Index: 4354468 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5802. Min Act: -0.1700
Data Index: 2614425 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.6427. Min Act: -0.1700
Data Index: 6848698 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5802. Min Act: -0.1700
Data Index: 3417893 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5802. Min Act: -0.1700
Data Index: 3907907 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5177. Min Act: -0.1700
Data Index: 7433705 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5177. Min Act: -0.1700
Data Index: 3832869 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5177. Min Act: -0.1700
Data Index: 5403033 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5177. Min Act: -0.1700
Data Index: 2853210 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.5177. Min Act: -0.1700
Data Index: 1021321 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.4552. Min Act: -0.1699
Data Index: 1298368 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.4552. Min Act: -0.1700
Data Index: 4345404 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8927. Min Range: -11.8927
Max Act: 11.4552. Min Act: -0.1673
Data Index: 5395100 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19