Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1900 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9847. Min Act: -0.1700
Data Index: 7669267 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9847. Min Act: -0.1700
Data Index: 2900708 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9534. Min Act: -0.1700
Data Index: 8597503 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9534. Min Act: -0.1700
Data Index: 2019406 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9378. Min Act: -0.1700
Data Index: 6219949 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9221. Min Act: -0.1700
Data Index: 1902351 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9065. Min Act: -0.1700
Data Index: 4748997 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9065. Min Act: -0.1700
Data Index: 7361074 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9065. Min Act: -0.1700
Data Index: 6725535 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8909. Min Act: -0.1700
Data Index: 4229372 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8909. Min Act: -0.1700
Data Index: 4718960 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8752. Min Act: -0.1700
Data Index: 5947749 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8596. Min Act: -0.1700
Data Index: 3660555 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8752. Min Act: -0.1700
Data Index: 555464 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8752. Min Act: -0.1700
Data Index: 2501567 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8752. Min Act: -0.1700
Data Index: 5374402 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8752. Min Act: -0.1700
Data Index: 7715873 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8596. Min Act: -0.1700
Data Index: 2400998 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8596. Min Act: -0.1700
Data Index: 6489326 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8596. Min Act: -0.1700
Data Index: 4327839 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19