Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.8740. Min Act: -0.1699
Data Index: 5789383 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.8398. Min Act: -0.1700
Data Index: 1324523 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.8398. Min Act: -0.1700
Data Index: 4962547 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.8398. Min Act: -0.1700
Data Index: 8623428 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.8054. Min Act: -0.1700
Data Index: 4681538 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7882. Min Act: -0.1700
Data Index: 307768 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7710. Min Act: -0.1700
Data Index: 3298447 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7710. Min Act: -0.1700
Data Index: 7595680 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7710. Min Act: -0.1700
Data Index: 4451474 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7537. Min Act: -0.1700
Data Index: 5844978 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7537. Min Act: -0.1700
Data Index: 7234384 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7365. Min Act: -0.1700
Data Index: 194103 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7018. Min Act: -0.1700
Data Index: 40786 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7018. Min Act: -0.1700
Data Index: 448896 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.6845. Min Act: -0.1700
Data Index: 4725381 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.6671. Min Act: -0.1700
Data Index: 5563352 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.7018. Min Act: -0.1700
Data Index: 2086600 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.6671. Min Act: -0.1700
Data Index: 5952536 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.6671. Min Act: -0.1700
Data Index: 315317 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8740. Min Range: -1.8740
Max Act: 1.6671. Min Act: -0.1699
Data Index: 4560323 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19