Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.4439. Min Act: -0.1700
Data Index: 62845 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.4127. Min Act: -0.1700
Data Index: 2906881 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.3814. Min Act: -0.1700
Data Index: 811202 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.3814. Min Act: -0.1700
Data Index: 6030834 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.2877. Min Act: -0.1700
Data Index: 3380609 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.3189. Min Act: -0.1700
Data Index: 911408 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.2564. Min Act: -0.1700
Data Index: 6568817 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.2252. Min Act: -0.1700
Data Index: 2876661 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.2252. Min Act: -0.1700
Data Index: 2559466 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1627. Min Act: -0.1700
Data Index: 5114709 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1627. Min Act: -0.1700
Data Index: 4914800 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1627. Min Act: -0.1700
Data Index: 6352956 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1627. Min Act: -0.1700
Data Index: 1704234 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1002. Min Act: -0.1700
Data Index: 7539784 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1314. Min Act: -0.1700
Data Index: 77324 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1002. Min Act: -0.1700
Data Index: 4961196 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1314. Min Act: -0.1700
Data Index: 5584480 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1002. Min Act: -0.1700
Data Index: 1054533 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.1002. Min Act: -0.1700
Data Index: 3240601 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4439. Min Range: -5.4439
Max Act: 5.0689. Min Act: -0.1700
Data Index: 6273240 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19