Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5502. Min Range: -10.5502
Max Act: 10.5502. Min Act: -0.1700
Data Index: 3070670 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5502. Min Range: -10.5502
Max Act: 10.3627. Min Act: -0.1700
Data Index: 8201451 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.9877. Min Act: -0.1700
Data Index: 5528924 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.9252. Min Act: -0.1700
Data Index: 4379371 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.8627. Min Act: -0.1700
Data Index: 1784208 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.8627. Min Act: -0.1700
Data Index: 6340437 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.8627. Min Act: -0.1700
Data Index: 4766931 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.8002. Min Act: -0.1700
Data Index: 1628172 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.8002. Min Act: -0.1700
Data Index: 8354945 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.8002. Min Act: -0.1700
Data Index: 3428551 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.7377. Min Act: -0.1700
Data Index: 6151234 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6752. Min Act: -0.1700
Data Index: 3268082 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6752. Min Act: -0.1700
Data Index: 95408 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6127. Min Act: -0.1700
Data Index: 8069170 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6127. Min Act: -0.1700
Data Index: 6666055 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6127. Min Act: -0.1700
Data Index: 5944808 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6127. Min Act: -0.1700
Data Index: 3760932 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6127. Min Act: -0.1700
Data Index: 3609464 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6127. Min Act: -0.1700
Data Index: 2809698 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5502. Min Range: -10.5502
Max Act: 9.6127. Min Act: -0.1700
Data Index: 5124492 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19