Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3374 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1010. Min Range: -8.1010
Max Act: 8.1010. Min Act: -0.1700
Data Index: 4943586 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1010. Min Range: -8.1010
Max Act: 8.0073. Min Act: -0.1700
Data Index: 5945624 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.8198. Min Act: -0.1700
Data Index: 3168785 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.8198. Min Act: -0.1700
Data Index: 739448 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.6948. Min Act: -0.1700
Data Index: 2977614 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.6323. Min Act: -0.1700
Data Index: 8339725 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.5385. Min Act: -0.1700
Data Index: 4304317 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.5385. Min Act: -0.1700
Data Index: 615181 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.5073. Min Act: -0.1700
Data Index: 8704660 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.4760. Min Act: -0.1700
Data Index: 6672983 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.5073. Min Act: -0.1700
Data Index: 2077891 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.4448. Min Act: -0.1700
Data Index: 3449676 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.4448. Min Act: -0.1700
Data Index: 8282821 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.4135. Min Act: -0.1700
Data Index: 1772899 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.4135. Min Act: -0.1700
Data Index: 1248296 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.4135. Min Act: -0.1700
Data Index: 692767 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.4135. Min Act: -0.1700
Data Index: 7844283 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.3510. Min Act: -0.1700
Data Index: 8771605 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.3510. Min Act: -0.1700
Data Index: 3352838 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1010. Min Range: -8.1010
Max Act: 7.3510. Min Act: -0.1700
Data Index: 5679715 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19