Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.7977. Min Act: -0.1700
Data Index: 1899316 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.6727. Min Act: -0.1700
Data Index: 1565870 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.5477. Min Act: -0.1700
Data Index: 2778296 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.5164. Min Act: -0.1700
Data Index: 5154839 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.4539. Min Act: -0.1700
Data Index: 3386839 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3914. Min Act: -0.1700
Data Index: 7330058 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3914. Min Act: -0.1700
Data Index: 2125031 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3602. Min Act: -0.1700
Data Index: 6798072 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3602. Min Act: -0.1700
Data Index: 946758 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3289. Min Act: -0.1700
Data Index: 5942148 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3289. Min Act: -0.1700
Data Index: 8246048 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3602. Min Act: -0.1700
Data Index: 4747143 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.2977. Min Act: -0.1700
Data Index: 3586194 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3289. Min Act: -0.1700
Data Index: 5390500 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.3289. Min Act: -0.1700
Data Index: 3538072 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.2977. Min Act: -0.1700
Data Index: 4820685 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.2352. Min Act: -0.1700
Data Index: 8455888 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.2352. Min Act: -0.1700
Data Index: 3066188 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.2039. Min Act: -0.1700
Data Index: 93862 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7977. Min Range: -6.7977
Max Act: 6.2039. Min Act: -0.1700
Data Index: 2940464 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19