Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2106 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.3541. Min Act: -0.1700
Data Index: 4550051 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.3541. Min Act: -0.1700
Data Index: 1244880 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.1979. Min Act: -0.1700
Data Index: 8296529 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.1666. Min Act: -0.1700
Data Index: 1198296 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.1354. Min Act: -0.1700
Data Index: 7028696 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.0729. Min Act: -0.1700
Data Index: 3130787 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.0416. Min Act: -0.1700
Data Index: 8167520 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.0416. Min Act: -0.1700
Data Index: 1607355 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.0416. Min Act: -0.1700
Data Index: 6444436 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.0104. Min Act: -0.1698
Data Index: 6796918 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3541. Min Range: -8.3541
Max Act: 8.0104. Min Act: -0.1700
Data Index: 5805294 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.9166. Min Act: -0.1700
Data Index: 5296828 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.8541. Min Act: -0.1700
Data Index: 6839039 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.8541. Min Act: -0.1699
Data Index: 3130798 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.8854. Min Act: -0.1700
Data Index: 7025641 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.8541. Min Act: -0.1700
Data Index: 6214442 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.8229. Min Act: -0.1700
Data Index: 1123067 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.8229. Min Act: -0.1700
Data Index: 8556301 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.7916. Min Act: -0.1700
Data Index: 4104248 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3541. Min Range: -8.3541
Max Act: 7.8229. Min Act: -0.1700
Data Index: 611068 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19