Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1707. Min Range: -7.1707
Max Act: 7.1707. Min Act: -0.1700
Data Index: 6237193 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.7020. Min Act: -0.1700
Data Index: 6665878 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.7020. Min Act: -0.1700
Data Index: 639179 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.6707. Min Act: -0.1700
Data Index: 6438247 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.5457. Min Act: -0.1700
Data Index: 624442 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.4520. Min Act: -0.1700
Data Index: 4503083 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.4207. Min Act: -0.1700
Data Index: 5005361 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.4520. Min Act: -0.1700
Data Index: 6495856 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.3895. Min Act: -0.1700
Data Index: 5227042 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.3895. Min Act: -0.1700
Data Index: 1825237 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.3582. Min Act: -0.1700
Data Index: 8033606 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.3270. Min Act: -0.1700
Data Index: 1145708 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.2957. Min Act: -0.1700
Data Index: 3525025 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.3270. Min Act: -0.1700
Data Index: 4956325 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.3270. Min Act: -0.1700
Data Index: 904426 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 685872 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 2771468 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 7247536 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.2332. Min Act: -0.1700
Data Index: 2131848 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1707. Min Range: -7.1707
Max Act: 6.2020. Min Act: -0.1700
Data Index: 702836 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19