Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2666. Min Range: -8.2666
Max Act: 8.2666. Min Act: -0.1700
Data Index: 3650521 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.8603. Min Act: -0.1700
Data Index: 5187563 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.8291. Min Act: -0.1700
Data Index: 3335832 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.8291. Min Act: -0.1700
Data Index: 5885549 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.7666. Min Act: -0.1700
Data Index: 1794970 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.7978. Min Act: -0.1700
Data Index: 2198006 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.6728. Min Act: -0.1700
Data Index: 2976726 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.6103. Min Act: -0.1700
Data Index: 7205876 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.6103. Min Act: -0.1700
Data Index: 5229348 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.6103. Min Act: -0.1700
Data Index: 2112467 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5478. Min Act: -0.1700
Data Index: 7233087 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.6103. Min Act: -0.1700
Data Index: 505632 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.6103. Min Act: -0.1700
Data Index: 5389426 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5478. Min Act: -0.1700
Data Index: 7451515 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5478. Min Act: -0.1700
Data Index: 504914 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5478. Min Act: -0.1700
Data Index: 4420312 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5166. Min Act: -0.1700
Data Index: 8027984 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5791. Min Act: -0.1700
Data Index: 6635661 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5791. Min Act: -0.1700
Data Index: 1737388 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2666. Min Range: -8.2666
Max Act: 7.5166. Min Act: -0.1700
Data Index: 6283511 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19