Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.8534. Min Act: -0.1700
Data Index: 4919739 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.8222. Min Act: -0.1700
Data Index: 636754 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.8222. Min Act: -0.1700
Data Index: 4551040 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7909. Min Act: -0.1700
Data Index: 6448651 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7909. Min Act: -0.1700
Data Index: 2837518 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 7702769 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7597. Min Act: -0.1700
Data Index: 6974196 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 7186899 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6972. Min Act: -0.1700
Data Index: 3894612 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6972. Min Act: -0.1700
Data Index: 4032784 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.7284. Min Act: -0.1700
Data Index: 7562244 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6659. Min Act: -0.1700
Data Index: 3979616 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6659. Min Act: -0.1700
Data Index: 7304523 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6659. Min Act: -0.1700
Data Index: 7561037 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6659. Min Act: -0.1700
Data Index: 4593643 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6347. Min Act: -0.1700
Data Index: 4887377 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6347. Min Act: -0.1700
Data Index: 3507753 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6347. Min Act: -0.1700
Data Index: 5290779 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6347. Min Act: -0.1700
Data Index: 3367748 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8534. Min Range: -5.8534
Max Act: 5.6347. Min Act: -0.1700
Data Index: 5667532 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19