Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1045 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.9670. Min Act: -0.1700
Data Index: 5150952 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.9353. Min Act: -0.1700
Data Index: 3981674 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.8878. Min Act: -0.1700
Data Index: 5581023 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.9353. Min Act: -0.1700
Data Index: 3823556 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.8242. Min Act: -0.1700
Data Index: 4149035 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.8083. Min Act: -0.1700
Data Index: 1253469 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.7924. Min Act: -0.1700
Data Index: 5638073 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.7764. Min Act: -0.1700
Data Index: 5014890 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.7605. Min Act: -0.1700
Data Index: 4161721 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.7286. Min Act: -0.1700
Data Index: 5307642 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.7286. Min Act: -0.1700
Data Index: 1069833 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6164. Min Act: -0.1700
Data Index: 8748856 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6806. Min Act: -0.1700
Data Index: 7566246 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6485. Min Act: -0.1700
Data Index: 1590808 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6645. Min Act: -0.1700
Data Index: 6016038 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6645. Min Act: -0.1700
Data Index: 7087405 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6324. Min Act: -0.1700
Data Index: 8026521 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6645. Min Act: -0.1700
Data Index: 6316675 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6324. Min Act: -0.1700
Data Index: 6182830 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9670. Min Range: -2.9670
Max Act: 2.6485. Min Act: -0.1700
Data Index: 1624065 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19