Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 416 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4404. Min Range: -9.4404
Max Act: 9.4404. Min Act: -0.1700
Data Index: 3879632 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4404. Min Range: -9.4404
Max Act: 9.2529. Min Act: -0.1700
Data Index: 3927339 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.9404. Min Act: -0.1700
Data Index: 614859 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.8154. Min Act: -0.1700
Data Index: 7397308 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.8154. Min Act: -0.1700
Data Index: 2198871 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.7529. Min Act: -0.1700
Data Index: 3995286 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.7529. Min Act: -0.1700
Data Index: 4029005 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.8154. Min Act: -0.1700
Data Index: 5321232 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.6279. Min Act: -0.1700
Data Index: 2666698 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.6279. Min Act: -0.1699
Data Index: 5816741 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.6279. Min Act: -0.1700
Data Index: 3337155 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.5029. Min Act: -0.1700
Data Index: 180015 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.5654. Min Act: -0.1700
Data Index: 4604970 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.5654. Min Act: -0.1700
Data Index: 3889007 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.5654. Min Act: -0.1700
Data Index: 2934912 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.5029. Min Act: -0.1700
Data Index: 4729347 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.4404. Min Act: -0.1700
Data Index: 7049972 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.5029. Min Act: -0.1700
Data Index: 2800880 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.4404. Min Act: -0.1700
Data Index: 1125765 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4404. Min Range: -9.4404
Max Act: 8.5029. Min Act: -0.1700
Data Index: 688923 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19