Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4508 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0152. Min Range: -8.0152
Max Act: 8.0152. Min Act: -0.1700
Data Index: 6172517 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.9215. Min Act: -0.1700
Data Index: 4360638 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.7965. Min Act: -0.1700
Data Index: 5569737 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.7027. Min Act: -0.1700
Data Index: 2276716 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.6402. Min Act: -0.1700
Data Index: 6774470 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.6090. Min Act: -0.1700
Data Index: 3329041 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.6090. Min Act: -0.1700
Data Index: 1030542 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.6402. Min Act: -0.1700
Data Index: 1077627 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.5777. Min Act: -0.1700
Data Index: 2776349 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.5152. Min Act: -0.1700
Data Index: 3521897 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.4840. Min Act: -0.1700
Data Index: 3113836 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.4840. Min Act: -0.1700
Data Index: 5052305 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.4840. Min Act: -0.1700
Data Index: 3275652 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.4215. Min Act: -0.1700
Data Index: 5873853 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.4215. Min Act: -0.1700
Data Index: 2957664 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.4215. Min Act: -0.1700
Data Index: 2415024 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.4215. Min Act: -0.1700
Data Index: 8768352 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.3902. Min Act: -0.1700
Data Index: 7767111 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.3590. Min Act: -0.1700
Data Index: 5422853 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0152. Min Range: -8.0152
Max Act: 7.3590. Min Act: -0.1700
Data Index: 2920735 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19