Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.2200. Min Act: -0.1700
Data Index: 8528521 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.2200. Min Act: -0.1700
Data Index: 3302746 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 1618601 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1868. Min Act: -0.1700
Data Index: 1618599 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1369. Min Act: -0.1700
Data Index: 5682083 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 5325374 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 7523908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 3447920 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 1738852 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 4197167 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1369. Min Act: -0.1700
Data Index: 7103020 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 7734734 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 7659332 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 3443230 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1702. Min Act: -0.1700
Data Index: 5414245 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1369. Min Act: -0.1700
Data Index: 1995044 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1535. Min Act: -0.1700
Data Index: 2881046 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1202. Min Act: -0.1700
Data Index: 1882904 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1202. Min Act: -0.1700
Data Index: 8447302 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2200. Min Range: -2.2200
Max Act: 2.1202. Min Act: -0.1700
Data Index: 4667118 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19