Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3949 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1749. Min Range: -4.1749
Max Act: 4.1749. Min Act: -0.1700
Data Index: 6444340 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1749. Min Range: -4.1749
Max Act: 4.1437. Min Act: -0.1700
Data Index: 2666968 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1749. Min Range: -4.1749
Max Act: 4.0187. Min Act: -0.1700
Data Index: 7186547 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9874. Min Act: -0.1700
Data Index: 1299010 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9874. Min Act: -0.1700
Data Index: 8638693 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9874. Min Act: -0.1700
Data Index: 1879371 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9874. Min Act: -0.1700
Data Index: 17884 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9561. Min Act: -0.1700
Data Index: 2459118 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9561. Min Act: -0.1700
Data Index: 8217095 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9249. Min Act: -0.1700
Data Index: 150020 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9249. Min Act: -0.1700
Data Index: 6055510 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9249. Min Act: -0.1700
Data Index: 3191502 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9249. Min Act: -0.1700
Data Index: 7723647 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.9249. Min Act: -0.1700
Data Index: 2872703 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.8780. Min Act: -0.1700
Data Index: 7434540 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.8936. Min Act: -0.1700
Data Index: 4847908 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.8467. Min Act: -0.1700
Data Index: 6718983 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.8623. Min Act: -0.1700
Data Index: 7518586 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.8623. Min Act: -0.1700
Data Index: 6992110 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1749. Min Range: -4.1749
Max Act: 3.8467. Min Act: -0.1700
Data Index: 7185880 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19