Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4187 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.7256. Min Act: -0.1700
Data Index: 7933466 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.6631. Min Act: -0.1700
Data Index: 3280388 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.6318. Min Act: -0.1700
Data Index: 1871622 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.6318. Min Act: -0.1700
Data Index: 1103121 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.6006. Min Act: -0.1700
Data Index: 2966670 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5693. Min Act: -0.1700
Data Index: 2398886 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5693. Min Act: -0.1700
Data Index: 5916316 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5693. Min Act: -0.1700
Data Index: 4085923 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5693. Min Act: -0.1700
Data Index: 7392218 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1698
Data Index: 8219384 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 5330744 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 916538 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 129209 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 5976506 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 757853 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 1662141 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5068. Min Act: -0.1700
Data Index: 7125758 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1699
Data Index: 7372957 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 573714 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7256. Min Range: -4.7256
Max Act: 4.5381. Min Act: -0.1700
Data Index: 3062474 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19