Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 641 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.2351. Min Act: -0.1700
Data Index: 7881831 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.2351. Min Act: -0.1700
Data Index: 8074104 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.1726. Min Act: -0.1700
Data Index: 1366293 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.1101. Min Act: -0.1700
Data Index: 1916066 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.1101. Min Act: -0.1700
Data Index: 2423475 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.0476. Min Act: -0.1700
Data Index: 2372185 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.0476. Min Act: -0.1700
Data Index: 3499491 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9851. Min Act: -0.1700
Data Index: 5135986 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2351. Min Range: -9.2351
Max Act: 9.0476. Min Act: -0.1700
Data Index: 4058704 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9226. Min Act: -0.1700
Data Index: 203472 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9851. Min Act: -0.1700
Data Index: 2410673 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9226. Min Act: -0.1700
Data Index: 2973712 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9851. Min Act: -0.1700
Data Index: 3138384 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9226. Min Act: -0.1700
Data Index: 395573 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9226. Min Act: -0.1700
Data Index: 1152563 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.9226. Min Act: -0.1700
Data Index: 1653298 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.8601. Min Act: -0.1700
Data Index: 944584 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.7976. Min Act: -0.1700
Data Index: 2387591 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.8601. Min Act: -0.1700
Data Index: 6343973 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2351. Min Range: -9.2351
Max Act: 8.8601. Min Act: -0.1700
Data Index: 7143160 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #19