Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1910 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.1729. Min Act: -0.1700
Data Index: 8214761 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.1104. Min Act: -0.1700
Data Index: 7786855 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.1104. Min Act: -0.1699
Data Index: 6577915 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.0791. Min Act: -0.1700
Data Index: 5686002 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.0791. Min Act: -0.1700
Data Index: 7785025 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.1104. Min Act: -0.1700
Data Index: 6835295 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.0479. Min Act: -0.1700
Data Index: 1598108 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.0166. Min Act: -0.1700
Data Index: 3225010 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1729. Min Range: -6.1729
Max Act: 6.0166. Min Act: -0.1700
Data Index: 5747123 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 8182666 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 4519701 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 5686005 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 3700469 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 3738833 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9854. Min Act: -0.1700
Data Index: 6814588 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9541. Min Act: -0.1700
Data Index: 3924280 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9541. Min Act: -0.1700
Data Index: 154433 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9541. Min Act: -0.1700
Data Index: 4672086 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9541. Min Act: -0.1700
Data Index: 4628733 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1729. Min Range: -6.1729
Max Act: 5.9541. Min Act: -0.1700
Data Index: 4230582 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19