Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 568 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2760. Min Range: -10.2760
Max Act: 10.2760. Min Act: -0.1700
Data Index: 8145660 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2760. Min Range: -10.2760
Max Act: 10.0260. Min Act: -0.1700
Data Index: 7123327 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.9635. Min Act: -0.1700
Data Index: 298666 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.9635. Min Act: -0.1700
Data Index: 4750917 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.9010. Min Act: -0.1700
Data Index: 7836211 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.7135. Min Act: -0.1700
Data Index: 671870 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.7135. Min Act: -0.1700
Data Index: 5961330 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.7135. Min Act: -0.1700
Data Index: 5720459 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.5260. Min Act: -0.1700
Data Index: 3818292 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.4010. Min Act: -0.1700
Data Index: 1667688 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.3385. Min Act: -0.1700
Data Index: 8077821 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2760. Min Act: -0.1700
Data Index: 6558535 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2760. Min Act: -0.1700
Data Index: 3164704 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2760. Min Act: -0.1700
Data Index: 8077820 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2760. Min Act: -0.1700
Data Index: 4795573 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2135. Min Act: -0.1700
Data Index: 6558533 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2135. Min Act: -0.1700
Data Index: 7044503 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2760. Min Act: -0.1700
Data Index: 396429 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.1510. Min Act: -0.1700
Data Index: 782768 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2760. Min Range: -10.2760
Max Act: 9.2135. Min Act: -0.1700
Data Index: 396427 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19