Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2816 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.5649. Min Act: -0.1700
Data Index: 2036800 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.5337. Min Act: -0.1700
Data Index: 1512297 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.5337. Min Act: -0.1700
Data Index: 3501802 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.5024. Min Act: -0.1700
Data Index: 7682327 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.4399. Min Act: -0.1700
Data Index: 1250920 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2020837 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3462. Min Act: -0.1700
Data Index: 2906080 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3462. Min Act: -0.1700
Data Index: 7748949 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.3774. Min Act: -0.1700
Data Index: 2032225 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2837. Min Act: -0.1700
Data Index: 7775567 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2837. Min Act: -0.1700
Data Index: 2342261 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2212. Min Act: -0.1700
Data Index: 174749 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2524. Min Act: -0.1700
Data Index: 5486716 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2524. Min Act: -0.1700
Data Index: 4172400 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2524. Min Act: -0.1700
Data Index: 1782862 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2524. Min Act: -0.1700
Data Index: 2680381 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2212. Min Act: -0.1700
Data Index: 7975635 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.2212. Min Act: -0.1700
Data Index: 3279814 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.1899. Min Act: -0.1700
Data Index: 3059600 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5649. Min Range: -6.5649
Max Act: 6.1587. Min Act: -0.1700
Data Index: 7319871 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19