Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2360 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3493. Min Range: -9.3493
Max Act: 9.3493. Min Act: -0.1700
Data Index: 1707194 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3493. Min Range: -9.3493
Max Act: 9.1618. Min Act: -0.1700
Data Index: 5147072 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.9743. Min Act: -0.1698
Data Index: 6408530 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.8493. Min Act: -0.1700
Data Index: 6408531 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.8493. Min Act: -0.1700
Data Index: 56856 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.8493. Min Act: -0.1700
Data Index: 1730787 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.7868. Min Act: -0.1700
Data Index: 43378 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.7868. Min Act: -0.1700
Data Index: 7244420 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.7243. Min Act: -0.1700
Data Index: 4282042 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.7243. Min Act: -0.1700
Data Index: 3588634 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.7243. Min Act: -0.1700
Data Index: 1064167 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.5993. Min Act: -0.1700
Data Index: 2530913 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.7243. Min Act: -0.1700
Data Index: 3889151 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.6618. Min Act: -0.1700
Data Index: 6487739 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.6618. Min Act: -0.1700
Data Index: 607477 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.5993. Min Act: -0.1699
Data Index: 607464 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.6618. Min Act: -0.1680
Data Index: 6487734 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.6618. Min Act: -0.1699
Data Index: 4061492 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.6618. Min Act: -0.1700
Data Index: 2569937 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3493. Min Range: -9.3493
Max Act: 8.6618. Min Act: -0.1700
Data Index: 2569939 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19