Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.7473. Min Act: -0.1700
Data Index: 5834943 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.6223. Min Act: -0.1700
Data Index: 4153022 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.6536. Min Act: -0.1700
Data Index: 3960854 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.5598. Min Act: -0.1700
Data Index: 7254310 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4661. Min Act: -0.1700
Data Index: 3644754 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4661. Min Act: -0.1700
Data Index: 2915355 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4661. Min Act: -0.1700
Data Index: 8193101 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4661. Min Act: -0.1700
Data Index: 4967015 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4661. Min Act: -0.1700
Data Index: 6672593 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4661. Min Act: -0.1700
Data Index: 7771773 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4036. Min Act: -0.1700
Data Index: 7532274 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4348. Min Act: -0.1700
Data Index: 6622996 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4348. Min Act: -0.1700
Data Index: 1264410 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4036. Min Act: -0.1700
Data Index: 7953032 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.3723. Min Act: -0.1700
Data Index: 7667122 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4036. Min Act: -0.1700
Data Index: 760873 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4036. Min Act: -0.1700
Data Index: 7489052 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.3723. Min Act: -0.1700
Data Index: 2931881 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4036. Min Act: -0.1700
Data Index: 837562 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7473. Min Range: -4.7473
Max Act: 4.4036. Min Act: -0.1700
Data Index: 7771771 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19