Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4586 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.3861. Min Act: -0.1700
Data Index: 3990084 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.3236. Min Act: -0.1700
Data Index: 1483802 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.2611. Min Act: -0.1700
Data Index: 3385749 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.1986. Min Act: -0.1700
Data Index: 1964868 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.1674. Min Act: -0.1700
Data Index: 7932286 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.1049. Min Act: -0.1700
Data Index: 5207149 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.0736. Min Act: -0.1700
Data Index: 418825 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.0424. Min Act: -0.1700
Data Index: 2267986 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.0424. Min Act: -0.1700
Data Index: 5319362 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3861. Min Range: -6.3861
Max Act: 6.0424. Min Act: -0.1700
Data Index: 5663004 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9799. Min Act: -0.1700
Data Index: 5599979 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9799. Min Act: -0.1700
Data Index: 661839 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9486. Min Act: -0.1700
Data Index: 741848 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9799. Min Act: -0.1700
Data Index: 5507887 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9486. Min Act: -0.1700
Data Index: 4646289 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9486. Min Act: -0.1700
Data Index: 3224886 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9486. Min Act: -0.1700
Data Index: 4814489 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9799. Min Act: -0.1700
Data Index: 3419252 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.8861. Min Act: -0.1700
Data Index: 420290 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3861. Min Range: -6.3861
Max Act: 5.9174. Min Act: -0.1700
Data Index: 4451738 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19