Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6192 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.6588. Min Act: -0.1700
Data Index: 4664969 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.5963. Min Act: -0.1700
Data Index: 2465156 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.4088. Min Act: -0.1700
Data Index: 6042991 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.3463. Min Act: -0.1700
Data Index: 3378307 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.3463. Min Act: -0.1700
Data Index: 7450460 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.2838. Min Act: -0.1700
Data Index: 7916233 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.1588. Min Act: -0.1700
Data Index: 5191126 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.0338. Min Act: -0.1700
Data Index: 1313518 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6588. Min Range: -10.6588
Max Act: 10.0338. Min Act: -0.1700
Data Index: 5297320 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.8463. Min Act: -0.1700
Data Index: 1021898 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 4291478 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 3051323 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 3512037 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 4835298 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 5016336 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 3750961 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 8249015 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7838. Min Act: -0.1700
Data Index: 7687697 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7213. Min Act: -0.1700
Data Index: 7489446 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6588. Min Range: -10.6588
Max Act: 9.7213. Min Act: -0.1700
Data Index: 8053982 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #19