Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 802 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.7128. Min Act: -0.1700
Data Index: 3723132 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.5878. Min Act: -0.1700
Data Index: 3468795 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.5878. Min Act: -0.1700
Data Index: 5373277 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.4003. Min Act: -0.1700
Data Index: 5956347 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.4003. Min Act: -0.1700
Data Index: 476297 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.4003. Min Act: -0.1700
Data Index: 8647327 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.3378. Min Act: -0.1700
Data Index: 2919857 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.3378. Min Act: -0.1700
Data Index: 6559696 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.2753. Min Act: -0.1700
Data Index: 624291 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.2753. Min Act: -0.1700
Data Index: 5352439 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.2753. Min Act: -0.1700
Data Index: 7139255 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.2128. Min Act: -0.1700
Data Index: 4689829 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.2128. Min Act: -0.1700
Data Index: 4642572 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.2128. Min Act: -0.1700
Data Index: 2449472 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.2128. Min Act: -0.1700
Data Index: 8380643 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.0878. Min Act: -0.1700
Data Index: 1838159 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.1503. Min Act: -0.1700
Data Index: 6559699 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.1503. Min Act: -0.1700
Data Index: 1961439 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.1503. Min Act: -0.1700
Data Index: 8019540 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7128. Min Range: -8.7128
Max Act: 8.0878. Min Act: -0.1700
Data Index: 4676339 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19