Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1402. Min Range: -4.1402
Max Act: 4.1402. Min Act: -0.1700
Data Index: 2989638 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.9840. Min Act: -0.1700
Data Index: 6447688 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.9214. Min Act: -0.1700
Data Index: 7008882 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8902. Min Act: -0.1700
Data Index: 2084904 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8589. Min Act: -0.1700
Data Index: 8686893 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.9214. Min Act: -0.1700
Data Index: 2202934 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8589. Min Act: -0.1700
Data Index: 2572454 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8276. Min Act: -0.1700
Data Index: 7738349 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8433. Min Act: -0.1700
Data Index: 736708 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8433. Min Act: -0.1700
Data Index: 2421426 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8276. Min Act: -0.1700
Data Index: 4739719 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8276. Min Act: -0.1700
Data Index: 6296271 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8276. Min Act: -0.1700
Data Index: 7880041 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8120. Min Act: -0.1700
Data Index: 6835393 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8120. Min Act: -0.1700
Data Index: 2271833 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.8120. Min Act: -0.1700
Data Index: 532330 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.7964. Min Act: -0.1700
Data Index: 5147027 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.7807. Min Act: -0.1700
Data Index: 6956618 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.7651. Min Act: -0.1700
Data Index: 6343751 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1402. Min Range: -4.1402
Max Act: 3.7651. Min Act: -0.1700
Data Index: 8500020 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19