Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2281 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0973. Min Range: -7.0973
Max Act: 7.0973. Min Act: -0.1700
Data Index: 5217856 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0973. Min Range: -7.0973
Max Act: 7.0348. Min Act: -0.1700
Data Index: 604738 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0973. Min Range: -7.0973
Max Act: 7.0348. Min Act: -0.1700
Data Index: 791678 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0973. Min Range: -7.0973
Max Act: 7.0036. Min Act: -0.1700
Data Index: 8622705 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.9723. Min Act: -0.1700
Data Index: 566005 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.8786. Min Act: -0.1700
Data Index: 6868112 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.8161. Min Act: -0.1700
Data Index: 245529 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.7848. Min Act: -0.1700
Data Index: 80605 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.7848. Min Act: -0.1700
Data Index: 2046634 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.7223. Min Act: -0.1700
Data Index: 4449465 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.6911. Min Act: -0.1700
Data Index: 4647445 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.6911. Min Act: -0.1700
Data Index: 4759113 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.6598. Min Act: -0.1700
Data Index: 5896334 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.6598. Min Act: -0.1700
Data Index: 1994424 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.5973. Min Act: -0.1700
Data Index: 1743817 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.5661. Min Act: -0.1700
Data Index: 2054348 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.5661. Min Act: -0.1700
Data Index: 6739730 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.5036. Min Act: -0.1700
Data Index: 1036016 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.5036. Min Act: -0.1700
Data Index: 3044954 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0973. Min Range: -7.0973
Max Act: 6.4723. Min Act: -0.1700
Data Index: 6345083 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #19