Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.2239. Min Act: -0.1700
Data Index: 2898128 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.1614. Min Act: -0.1700
Data Index: 3474016 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.1614. Min Act: -0.1700
Data Index: 3650045 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 6306610 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.1301. Min Act: -0.1700
Data Index: 6627460 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.1301. Min Act: -0.1700
Data Index: 7203633 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.1301. Min Act: -0.1700
Data Index: 302001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 4681012 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0676. Min Act: -0.1700
Data Index: 5742558 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 5466950 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 5340195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0676. Min Act: -0.1700
Data Index: 4907108 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 1900977 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 1513757 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 1326969 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 1031287 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 4678096 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 611313 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0676. Min Act: -0.1700
Data Index: 855461 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2239. Min Range: -4.2239
Max Act: 4.0989. Min Act: -0.1700
Data Index: 4114859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19