Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.4753. Min Act: -0.1700
Data Index: 1611544 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.4440. Min Act: -0.1700
Data Index: 7772477 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.3503. Min Act: -0.1700
Data Index: 4872975 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.3190. Min Act: -0.1700
Data Index: 4646013 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.2565. Min Act: -0.1700
Data Index: 533983 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.2253. Min Act: -0.1700
Data Index: 2233280 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.2253. Min Act: -0.1700
Data Index: 7489939 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1940. Min Act: -0.1700
Data Index: 3244665 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.2253. Min Act: -0.1700
Data Index: 7623795 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1627. Min Act: -0.1700
Data Index: 3188719 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1627. Min Act: -0.1700
Data Index: 5318282 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1940. Min Act: -0.1700
Data Index: 5249768 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1940. Min Act: -0.1700
Data Index: 533980 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1940. Min Act: -0.1700
Data Index: 3815515 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1315. Min Act: -0.1700
Data Index: 6134085 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1627. Min Act: -0.1700
Data Index: 98400 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1315. Min Act: -0.1700
Data Index: 5325822 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1315. Min Act: -0.1700
Data Index: 2060660 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1627. Min Act: -0.1700
Data Index: 6091592 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4753. Min Range: -4.4753
Max Act: 4.1627. Min Act: -0.1700
Data Index: 5062343 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19