Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3198 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.3895. Min Act: -0.1700
Data Index: 6305440 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.2645. Min Act: -0.1700
Data Index: 2719135 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.2020. Min Act: -0.1700
Data Index: 5933767 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.1395. Min Act: -0.1700
Data Index: 7290584 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.1395. Min Act: -0.1700
Data Index: 7377577 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.1395. Min Act: -0.1700
Data Index: 6280724 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.1395. Min Act: -0.1700
Data Index: 930297 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.1395. Min Act: -0.1700
Data Index: 6342461 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.1395. Min Act: -0.1700
Data Index: 8001363 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.0770. Min Act: -0.1700
Data Index: 5045716 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.0145. Min Act: -0.1700
Data Index: 6796654 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.1395. Min Act: -0.1700
Data Index: 3388754 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.0145. Min Act: -0.1700
Data Index: 1464257 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.0145. Min Act: -0.1700
Data Index: 5628811 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.0145. Min Act: -0.1700
Data Index: 2119401 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.0145. Min Act: -0.1700
Data Index: 4961594 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3895. Min Range: -8.3895
Max Act: 7.9832. Min Act: -0.1700
Data Index: 294310 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3895. Min Range: -8.3895
Max Act: 7.9832. Min Act: -0.1700
Data Index: 3111607 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3895. Min Range: -8.3895
Max Act: 7.9832. Min Act: -0.1700
Data Index: 4969042 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3895. Min Range: -8.3895
Max Act: 8.0145. Min Act: -0.1700
Data Index: 6637585 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19