Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1914 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.8671. Min Act: -0.1700
Data Index: 8249500 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7733. Min Act: -0.1700
Data Index: 3677697 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7733. Min Act: -0.1700
Data Index: 4824458 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7421. Min Act: -0.1700
Data Index: 6061014 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7733. Min Act: -0.1700
Data Index: 171065 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7421. Min Act: -0.1700
Data Index: 5508254 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7421. Min Act: -0.1700
Data Index: 4770594 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 7108358 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7108. Min Act: -0.1700
Data Index: 1741074 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 8210327 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.7108. Min Act: -0.1700
Data Index: 1526858 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 6923988 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 8036734 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 2934990 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6796. Min Act: -0.1700
Data Index: 7352368 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 4070826 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.5858. Min Act: -0.1700
Data Index: 2387597 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6483. Min Act: -0.1700
Data Index: 7041980 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.5858. Min Act: -0.1700
Data Index: 5791463 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8671. Min Range: -6.8671
Max Act: 6.6171. Min Act: -0.1700
Data Index: 6563331 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19