Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 790 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.7124. Min Act: -0.1700
Data Index: 2436188 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.6811. Min Act: -0.1700
Data Index: 3576788 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.6811. Min Act: -0.1700
Data Index: 6647496 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.6498. Min Act: -0.1700
Data Index: 4322246 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.5403. Min Act: -0.1700
Data Index: 6308956 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4933. Min Act: -0.1700
Data Index: 2682874 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4620. Min Act: -0.1700
Data Index: 5719064 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4620. Min Act: -0.1700
Data Index: 3519088 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4620. Min Act: -0.1700
Data Index: 1998700 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4620. Min Act: -0.1700
Data Index: 2274464 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4149. Min Act: -0.1700
Data Index: 2806382 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4149. Min Act: -0.1700
Data Index: 7334466 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4306. Min Act: -0.1700
Data Index: 2064638 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4149. Min Act: -0.1700
Data Index: 1680734 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.4306. Min Act: -0.1700
Data Index: 1488434 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.3993. Min Act: -0.1700
Data Index: 2076165 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.3836. Min Act: -0.1700
Data Index: 8242811 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.3522. Min Act: -0.1700
Data Index: 1573661 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.3522. Min Act: -0.1700
Data Index: 6603398 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7124. Min Range: -3.7124
Max Act: 3.3365. Min Act: -0.1700
Data Index: 2459539 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19