Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 819 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.6115. Min Act: -0.1700
Data Index: 1598305 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.5177. Min Act: -0.1700
Data Index: 7545722 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.4240. Min Act: -0.1700
Data Index: 7751922 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.4240. Min Act: -0.1700
Data Index: 5964733 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3927. Min Act: -0.1700
Data Index: 754425 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3927. Min Act: -0.1700
Data Index: 6078189 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3927. Min Act: -0.1700
Data Index: 4529924 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3927. Min Act: -0.1700
Data Index: 2355847 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3927. Min Act: -0.1700
Data Index: 3416866 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3927. Min Act: -0.1700
Data Index: 386225 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3615. Min Act: -0.1700
Data Index: 4403855 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3615. Min Act: -0.1700
Data Index: 4757699 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3615. Min Act: -0.1700
Data Index: 122776 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3615. Min Act: -0.1700
Data Index: 1069070 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3302. Min Act: -0.1700
Data Index: 647478 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3302. Min Act: -0.1700
Data Index: 7768499 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3302. Min Act: -0.1700
Data Index: 2097263 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3302. Min Act: -0.1700
Data Index: 8622230 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3302. Min Act: -0.1700
Data Index: 1503785 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6115. Min Range: -4.6115
Max Act: 4.3302. Min Act: -0.1700
Data Index: 6735826 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19