Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4225 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.6597. Min Act: -0.1700
Data Index: 487181 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.6597. Min Act: -0.1700
Data Index: 8562255 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.5659. Min Act: -0.1700
Data Index: 4692928 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.5034. Min Act: -0.1700
Data Index: 6255391 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.4722. Min Act: -0.1700
Data Index: 3931952 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.4722. Min Act: -0.1700
Data Index: 7006269 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.4409. Min Act: -0.1700
Data Index: 7092278 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.4409. Min Act: -0.1700
Data Index: 6229007 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.4409. Min Act: -0.1700
Data Index: 8695612 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.4409. Min Act: -0.1700
Data Index: 1810045 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.4097. Min Act: -0.1700
Data Index: 3072115 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.3472. Min Act: -0.1700
Data Index: 5382879 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.3472. Min Act: -0.1700
Data Index: 2829820 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.3159. Min Act: -0.1700
Data Index: 7491419 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.2847. Min Act: -0.1700
Data Index: 2776 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.2847. Min Act: -0.1700
Data Index: 5356623 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.2847. Min Act: -0.1700
Data Index: 642114 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.2222. Min Act: -0.1700
Data Index: 1333840 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.2222. Min Act: -0.1700
Data Index: 7915315 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6597. Min Range: -7.6597
Max Act: 7.1909. Min Act: -0.1700
Data Index: 2005723 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19