Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0760. Min Range: -7.0760
Max Act: 7.0760. Min Act: -0.1700
Data Index: 5767507 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.8573. Min Act: -0.1700
Data Index: 8496837 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.6073. Min Act: -0.1700
Data Index: 6438891 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.6385. Min Act: -0.1700
Data Index: 603940 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.5448. Min Act: -0.1700
Data Index: 804089 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.5448. Min Act: -0.1700
Data Index: 3036863 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.4823. Min Act: -0.1700
Data Index: 8184119 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.4198. Min Act: -0.1700
Data Index: 5445301 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.4198. Min Act: -0.1700
Data Index: 8339068 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.4198. Min Act: -0.1700
Data Index: 4838438 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.4198. Min Act: -0.1700
Data Index: 7113436 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3885. Min Act: -0.1700
Data Index: 3727002 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3885. Min Act: -0.1700
Data Index: 7433074 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3573. Min Act: -0.1700
Data Index: 664383 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3573. Min Act: -0.1700
Data Index: 7307572 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3573. Min Act: -0.1700
Data Index: 6358466 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3573. Min Act: -0.1700
Data Index: 5231639 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3573. Min Act: -0.1700
Data Index: 4704465 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3573. Min Act: -0.1700
Data Index: 985230 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0760. Min Range: -7.0760
Max Act: 6.3260. Min Act: -0.1700
Data Index: 3553529 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19