Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2423 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2318. Min Range: -7.2318
Max Act: 7.2318. Min Act: -0.1700
Data Index: 4422298 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5274465 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7318. Min Act: -0.1700
Data Index: 7286220 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.7005. Min Act: -0.1700
Data Index: 1686393 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.6380. Min Act: -0.1700
Data Index: 5491966 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.6380. Min Act: -0.1700
Data Index: 6938585 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 707446 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 6838017 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.5130. Min Act: -0.1700
Data Index: 1209401 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.4505. Min Act: -0.1700
Data Index: 312647 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.4505. Min Act: -0.1700
Data Index: 328317 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.4505. Min Act: -0.1700
Data Index: 1657231 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.4505. Min Act: -0.1700
Data Index: 1592022 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.3880. Min Act: -0.1700
Data Index: 7342761 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.3568. Min Act: -0.1700
Data Index: 4260438 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.3568. Min Act: -0.1700
Data Index: 1500472 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.3255. Min Act: -0.1700
Data Index: 6604018 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.3255. Min Act: -0.1700
Data Index: 1179790 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.3255. Min Act: -0.1700
Data Index: 2510788 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2318. Min Range: -7.2318
Max Act: 6.2943. Min Act: -0.1700
Data Index: 823221 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19