Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3922 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.8402. Min Act: -0.1700
Data Index: 35530 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.5681. Min Act: -0.1700
Data Index: 3469557 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.4873. Min Act: -0.1700
Data Index: 7068580 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.4873. Min Act: -0.1700
Data Index: 3130829 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.4385. Min Act: -0.1700
Data Index: 7678139 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.4223. Min Act: -0.1700
Data Index: 3068989 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.4223. Min Act: -0.1700
Data Index: 6860798 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3896. Min Act: -0.1700
Data Index: 3069003 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.4060. Min Act: -0.1700
Data Index: 4752672 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3569. Min Act: -0.1700
Data Index: 1150226 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3733. Min Act: -0.1700
Data Index: 2481183 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3569. Min Act: -0.1700
Data Index: 4922766 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3733. Min Act: -0.1700
Data Index: 4187213 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3405. Min Act: -0.1700
Data Index: 5982504 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3241. Min Act: -0.1700
Data Index: 4637891 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3405. Min Act: -0.1700
Data Index: 5982508 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3241. Min Act: -0.1700
Data Index: 458340 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3241. Min Act: -0.1700
Data Index: 6330600 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3405. Min Act: -0.1700
Data Index: 8093120 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8402. Min Range: -2.8402
Max Act: 2.3077. Min Act: -0.1700
Data Index: 3130834 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19