Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2236 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.7778. Min Act: -0.1700
Data Index: 6102261 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.6528. Min Act: -0.1700
Data Index: 111594 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.6215. Min Act: -0.1700
Data Index: 5025328 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5590. Min Act: -0.1700
Data Index: 1716646 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5590. Min Act: -0.1700
Data Index: 149124 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5590. Min Act: -0.1700
Data Index: 6490962 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5590. Min Act: -0.1700
Data Index: 870491 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5590. Min Act: -0.1700
Data Index: 8613039 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 5757080 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5590. Min Act: -0.1700
Data Index: 7825772 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 7833945 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 3426371 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 1339152 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 4472717 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 6468799 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.4965. Min Act: -0.1700
Data Index: 1248062 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.4653. Min Act: -0.1700
Data Index: 1702648 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.4965. Min Act: -0.1700
Data Index: 2218353 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.5278. Min Act: -0.1700
Data Index: 8442508 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7778. Min Range: -6.7778
Max Act: 6.4965. Min Act: -0.1700
Data Index: 4583768 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19