Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 129 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.3325. Min Act: -0.1700
Data Index: 384872 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.3325. Min Act: -0.1700
Data Index: 1741734 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.3148. Min Act: -0.1700
Data Index: 64525 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.3325. Min Act: -0.1700
Data Index: 6556990 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.3148. Min Act: -0.1700
Data Index: 3751708 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2972. Min Act: -0.1700
Data Index: 2250876 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.3148. Min Act: -0.1700
Data Index: 413623 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 520469 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2972. Min Act: -0.1700
Data Index: 3708698 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2796. Min Act: -0.1700
Data Index: 4791779 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 3573102 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 4235663 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2796. Min Act: -0.1700
Data Index: 82610 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 2906989 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 8206997 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 6566210 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 2332993 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2443. Min Act: -0.1700
Data Index: 5236297 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2443. Min Act: -0.1700
Data Index: 4383632 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3325. Min Range: -1.3325
Max Act: 1.2619. Min Act: -0.1700
Data Index: 4740239 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19