Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3643 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9683. Min Range: -9.9683
Max Act: 9.9683. Min Act: -0.1700
Data Index: 3098224 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9683. Min Range: -9.9683
Max Act: 9.7808. Min Act: -0.1700
Data Index: 1567991 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9683. Min Range: -9.9683
Max Act: 9.4058. Min Act: -0.1700
Data Index: 2416092 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9683. Min Range: -9.9683
Max Act: 9.1558. Min Act: -0.1700
Data Index: 2058226 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9683. Min Range: -9.9683
Max Act: 9.0308. Min Act: -0.1700
Data Index: 3043020 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9683. Min Range: -9.9683
Max Act: 9.0308. Min Act: -0.1700
Data Index: 8828081 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.9683. Min Act: -0.1700
Data Index: 7805124 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9683. Min Range: -9.9683
Max Act: 9.0308. Min Act: -0.1700
Data Index: 1763208 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.9683. Min Act: -0.1700
Data Index: 517629 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.9683. Min Act: -0.1700
Data Index: 4878862 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.9058. Min Act: -0.1700
Data Index: 3898904 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.9058. Min Act: -0.1700
Data Index: 3501735 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.9058. Min Act: -0.1700
Data Index: 3994032 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.9058. Min Act: -0.1700
Data Index: 6462804 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.8433. Min Act: -0.1700
Data Index: 7251902 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.7808. Min Act: -0.1700
Data Index: 4287719 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.7183. Min Act: -0.1700
Data Index: 2020850 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.7183. Min Act: -0.1700
Data Index: 3551018 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.6558. Min Act: -0.1700
Data Index: 5152196 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9683. Min Range: -9.9683
Max Act: 8.7183. Min Act: -0.1700
Data Index: 640477 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19