Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3901 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.3006. Min Act: -0.1700
Data Index: 5036999 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2676. Min Act: -0.1700
Data Index: 3636526 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2511. Min Act: -0.1700
Data Index: 7515428 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2676. Min Act: -0.1700
Data Index: 1427084 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2676. Min Act: -0.1700
Data Index: 2936591 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2511. Min Act: -0.1700
Data Index: 2868339 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2511. Min Act: -0.1700
Data Index: 6833735 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2511. Min Act: -0.1700
Data Index: 5592291 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2346. Min Act: -0.1700
Data Index: 2871540 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2346. Min Act: -0.1700
Data Index: 4236918 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2180. Min Act: -0.1700
Data Index: 1026178 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2180. Min Act: -0.1700
Data Index: 85900 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2180. Min Act: -0.1700
Data Index: 5562078 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2180. Min Act: -0.1700
Data Index: 5154788 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2014. Min Act: -0.1700
Data Index: 6272677 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2014. Min Act: -0.1700
Data Index: 4006542 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.2014. Min Act: -0.1700
Data Index: 8577646 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.1848. Min Act: -0.1700
Data Index: 6386448 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.1848. Min Act: -0.1700
Data Index: 1425510 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3006. Min Range: -2.3006
Max Act: 2.1682. Min Act: -0.1700
Data Index: 5216949 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19