Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1274 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1481. Min Range: -9.1481
Max Act: 9.1481. Min Act: -0.1700
Data Index: 1222506 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.7731. Min Act: -0.1700
Data Index: 8602627 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.7731. Min Act: -0.1700
Data Index: 5570607 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.6481. Min Act: -0.1700
Data Index: 5250783 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.5856. Min Act: -0.1700
Data Index: 4400823 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.6481. Min Act: -0.1700
Data Index: 6646424 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.5856. Min Act: -0.1700
Data Index: 4232779 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.5856. Min Act: -0.1700
Data Index: 1921441 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.5856. Min Act: -0.1700
Data Index: 2437461 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.5231. Min Act: -0.1700
Data Index: 3412932 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 7950074 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 4544810 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 6837884 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.4606. Min Act: -0.1700
Data Index: 2429236 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 6746795 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 2142353 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 4563899 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 1921443 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 1295589 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1481. Min Range: -9.1481
Max Act: 8.3981. Min Act: -0.1700
Data Index: 4749784 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19