Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.9553. Min Act: -0.1700
Data Index: 2464648 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.9553. Min Act: -0.1700
Data Index: 4361199 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.8615. Min Act: -0.1700
Data Index: 3752613 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.7990. Min Act: -0.1700
Data Index: 220367 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.7678. Min Act: -0.1700
Data Index: 6710759 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.7678. Min Act: -0.1700
Data Index: 3238663 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.7365. Min Act: -0.1700
Data Index: 5613039 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.7365. Min Act: -0.1700
Data Index: 5947171 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.7053. Min Act: -0.1700
Data Index: 1735539 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.7053. Min Act: -0.1700
Data Index: 8347901 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.6740. Min Act: -0.1700
Data Index: 1736701 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.6740. Min Act: -0.1700
Data Index: 2100981 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.6740. Min Act: -0.1700
Data Index: 1706970 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.6428. Min Act: -0.1700
Data Index: 5405143 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.6428. Min Act: -0.1700
Data Index: 5075941 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.6115. Min Act: -0.1700
Data Index: 6933299 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.6115. Min Act: -0.1700
Data Index: 3673163 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.5803. Min Act: -0.1700
Data Index: 7285806 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.5803. Min Act: -0.1700
Data Index: 7462790 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9553. Min Range: -5.9553
Max Act: 5.5803. Min Act: -0.1700
Data Index: 4258575 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19