Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3000 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.7076. Min Act: -0.1700
Data Index: 938374 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.7076. Min Act: -0.1700
Data Index: 1706038 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.5513. Min Act: -0.1700
Data Index: 7645626 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.4263. Min Act: -0.1700
Data Index: 5488154 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.4263. Min Act: -0.1700
Data Index: 8167206 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3951. Min Act: -0.1700
Data Index: 1708676 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3638. Min Act: -0.1700
Data Index: 6446515 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3638. Min Act: -0.1700
Data Index: 656048 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3638. Min Act: -0.1700
Data Index: 7144937 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3326. Min Act: -0.1700
Data Index: 8167196 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 3568968 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 1805592 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 8167199 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 151439 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 8735575 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 541816 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 6744466 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 3059155 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.3013. Min Act: -0.1700
Data Index: 3428215 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7076. Min Range: -4.7076
Max Act: 4.2701. Min Act: -0.1700
Data Index: 2508500 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19