Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2675 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.5464. Min Act: -0.1700
Data Index: 5769275 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.3589. Min Act: -0.1700
Data Index: 1035365 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.2651. Min Act: -0.1700
Data Index: 8588326 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.2339. Min Act: -0.1700
Data Index: 5590112 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.2339. Min Act: -0.1700
Data Index: 1881640 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.2026. Min Act: -0.1700
Data Index: 1815550 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.1714. Min Act: -0.1700
Data Index: 400068 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.1401. Min Act: -0.1700
Data Index: 3820023 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.1401. Min Act: -0.1700
Data Index: 4241728 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.1089. Min Act: -0.1700
Data Index: 4161927 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.1089. Min Act: -0.1700
Data Index: 4841401 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.1089. Min Act: -0.1700
Data Index: 7807410 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.1089. Min Act: -0.1700
Data Index: 5542053 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.0776. Min Act: -0.1700
Data Index: 3566861 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.0776. Min Act: -0.1700
Data Index: 489689 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.0776. Min Act: -0.1700
Data Index: 3502701 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.0464. Min Act: -0.1700
Data Index: 5552595 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.0464. Min Act: -0.1700
Data Index: 7807409 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.0464. Min Act: -0.1700
Data Index: 6657295 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5464. Min Range: -5.5464
Max Act: 5.0151. Min Act: -0.1700
Data Index: 4322138 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19