Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4806 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3539. Min Range: -7.3539
Max Act: 7.3539. Min Act: -0.1700
Data Index: 283734 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.9164. Min Act: -0.1700
Data Index: 4420460 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.7914. Min Act: -0.1700
Data Index: 130775 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.7602. Min Act: -0.1700
Data Index: 7076151 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.7289. Min Act: -0.1700
Data Index: 8327146 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.7602. Min Act: -0.1700
Data Index: 5647323 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.7602. Min Act: -0.1700
Data Index: 896586 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.7289. Min Act: -0.1700
Data Index: 5995267 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.6977. Min Act: -0.1700
Data Index: 143607 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.6352. Min Act: -0.1700
Data Index: 4158942 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.6664. Min Act: -0.1700
Data Index: 5934172 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.6352. Min Act: -0.1700
Data Index: 2703612 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.6352. Min Act: -0.1700
Data Index: 6265863 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.5727. Min Act: -0.1700
Data Index: 1802659 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.5727. Min Act: -0.1700
Data Index: 641146 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.5102. Min Act: -0.1700
Data Index: 2290398 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.5102. Min Act: -0.1700
Data Index: 4364178 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.5414. Min Act: -0.1700
Data Index: 2358233 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.4789. Min Act: -0.1700
Data Index: 7524836 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3539. Min Range: -7.3539
Max Act: 6.4477. Min Act: -0.1700
Data Index: 1565052 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19