Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.5556. Min Act: -0.1700
Data Index: 135326 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.4618. Min Act: -0.1700
Data Index: 2330894 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.4306. Min Act: -0.1700
Data Index: 1959951 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.3681. Min Act: -0.1700
Data Index: 7477215 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.3368. Min Act: -0.1700
Data Index: 8460893 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.2431. Min Act: -0.1700
Data Index: 6933189 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.2431. Min Act: -0.1700
Data Index: 1143574 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.2118. Min Act: -0.1700
Data Index: 7499452 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1806. Min Act: -0.1700
Data Index: 5609920 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1806. Min Act: -0.1700
Data Index: 5787560 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1493. Min Act: -0.1700
Data Index: 4047310 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1493. Min Act: -0.1700
Data Index: 6759743 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1181. Min Act: -0.1700
Data Index: 6546901 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1493. Min Act: -0.1700
Data Index: 5284037 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1181. Min Act: -0.1700
Data Index: 475738 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.1493. Min Act: -0.1700
Data Index: 5068466 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.0868. Min Act: -0.1700
Data Index: 3300928 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.0868. Min Act: -0.1700
Data Index: 5499410 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.0868. Min Act: -0.1700
Data Index: 3202223 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5556. Min Range: -5.5556
Max Act: 5.0556. Min Act: -0.1700
Data Index: 2306184 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19