Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 266 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8980. Min Act: -0.1700
Data Index: 5475255 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8355. Min Act: -0.1700
Data Index: 4056333 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8355. Min Act: -0.1700
Data Index: 297338 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8355. Min Act: -0.1700
Data Index: 3038291 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7730. Min Act: -0.1700
Data Index: 1041628 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8042. Min Act: -0.1700
Data Index: 5808075 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.8042. Min Act: -0.1700
Data Index: 7203063 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7417. Min Act: -0.1700
Data Index: 2148897 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7730. Min Act: -0.1700
Data Index: 5460866 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 6372196 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7417. Min Act: -0.1700
Data Index: 8324904 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 4587435 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 223990 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 5298 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.7105. Min Act: -0.1700
Data Index: 1515870 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 14274 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6480. Min Act: -0.1700
Data Index: 6729401 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 4495796 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 6827735 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8980. Min Range: -4.8980
Max Act: 4.6792. Min Act: -0.1700
Data Index: 5258363 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19