Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3575 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.7565. Min Act: -0.1700
Data Index: 5792506 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.5690. Min Act: -0.1700
Data Index: 7377061 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.5065. Min Act: -0.1700
Data Index: 8472326 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.4440. Min Act: -0.1700
Data Index: 7218781 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.3815. Min Act: -0.1700
Data Index: 7114885 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.3190. Min Act: -0.1700
Data Index: 1499804 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.2565. Min Act: -0.1700
Data Index: 3977922 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.1940. Min Act: -0.1700
Data Index: 1359289 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.1940. Min Act: -0.1700
Data Index: 437753 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.1940. Min Act: -0.1700
Data Index: 5792507 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.1940. Min Act: -0.1700
Data Index: 6660635 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.1940. Min Act: -0.1700
Data Index: 7055527 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.1315. Min Act: -0.1700
Data Index: 5775836 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.1315. Min Act: -0.1700
Data Index: 7606189 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.0690. Min Act: -0.1700
Data Index: 2985787 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.0690. Min Act: -0.1700
Data Index: 2681384 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.0690. Min Act: -0.1700
Data Index: 8387643 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.0065. Min Act: -0.1700
Data Index: 7208294 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.0065. Min Act: -0.1700
Data Index: 4978210 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7565. Min Range: -8.7565
Max Act: 8.0065. Min Act: -0.1700
Data Index: 3183659 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19