Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2895. Min Range: -7.2895
Max Act: 7.2895. Min Act: -0.1700
Data Index: 7868895 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2895. Min Range: -7.2895
Max Act: 7.0395. Min Act: -0.1700
Data Index: 3656101 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2895. Min Range: -7.2895
Max Act: 7.0707. Min Act: -0.1700
Data Index: 6105419 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.8832. Min Act: -0.1700
Data Index: 492685 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.8832. Min Act: -0.1700
Data Index: 5337446 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.8520. Min Act: -0.1700
Data Index: 6623621 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.8832. Min Act: -0.1700
Data Index: 47448 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.7895. Min Act: -0.1700
Data Index: 3840089 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.7582. Min Act: -0.1700
Data Index: 8311796 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.7270. Min Act: -0.1700
Data Index: 6826700 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.7582. Min Act: -0.1700
Data Index: 6222187 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.7270. Min Act: -0.1700
Data Index: 7509599 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.7582. Min Act: -0.1700
Data Index: 7114722 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.6957. Min Act: -0.1700
Data Index: 1210226 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.6645. Min Act: -0.1700
Data Index: 1979441 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.6957. Min Act: -0.1700
Data Index: 766360 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.6957. Min Act: -0.1700
Data Index: 3334783 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.6957. Min Act: -0.1700
Data Index: 6115704 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.6645. Min Act: -0.1700
Data Index: 165956 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2895. Min Range: -7.2895
Max Act: 6.6645. Min Act: -0.1700
Data Index: 625975 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19