Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3369 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.4817. Min Act: -0.1700
Data Index: 3234070 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.4817. Min Act: -0.1700
Data Index: 2343507 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3880. Min Act: -0.1700
Data Index: 8423166 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3880. Min Act: -0.1700
Data Index: 6430214 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2942. Min Act: -0.1700
Data Index: 3368790 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2942. Min Act: -0.1700
Data Index: 1471308 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2630. Min Act: -0.1700
Data Index: 8290365 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2317. Min Act: -0.1700
Data Index: 5234829 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2317. Min Act: -0.1700
Data Index: 8123803 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1692. Min Act: -0.1700
Data Index: 7830187 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2005. Min Act: -0.1700
Data Index: 2937059 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2005. Min Act: -0.1700
Data Index: 841992 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2005. Min Act: -0.1700
Data Index: 3131992 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1692. Min Act: -0.1700
Data Index: 8745708 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1380. Min Act: -0.1700
Data Index: 2056292 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1380. Min Act: -0.1700
Data Index: 7922403 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1380. Min Act: -0.1700
Data Index: 6330019 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1067. Min Act: -0.1700
Data Index: 3616049 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1067. Min Act: -0.1700
Data Index: 5753597 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.1067. Min Act: -0.1700
Data Index: 8053781 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19