Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2645 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.3724. Min Act: -0.1700
Data Index: 4624542 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.3412. Min Act: -0.1700
Data Index: 7285466 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.3412. Min Act: -0.1700
Data Index: 101005 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.2787. Min Act: -0.1700
Data Index: 7879437 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.2787. Min Act: -0.1700
Data Index: 3462381 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1849. Min Act: -0.1700
Data Index: 4073225 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1224. Min Act: -0.1700
Data Index: 5584524 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1537. Min Act: -0.1700
Data Index: 5997344 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1224. Min Act: -0.1700
Data Index: 1140034 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.0912. Min Act: -0.1700
Data Index: 5171421 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1537. Min Act: -0.1700
Data Index: 1274053 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1224. Min Act: -0.1700
Data Index: 906835 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1224. Min Act: -0.1700
Data Index: 6434475 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.0912. Min Act: -0.1700
Data Index: 8675701 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1224. Min Act: -0.1700
Data Index: 3865478 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1537. Min Act: -0.1700
Data Index: 7535898 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1224. Min Act: -0.1700
Data Index: 6643523 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.0599. Min Act: -0.1700
Data Index: 3431071 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.0912. Min Act: -0.1700
Data Index: 7148084 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3724. Min Range: -5.3724
Max Act: 5.1224. Min Act: -0.1700
Data Index: 3123984 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19