Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 686 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3655. Min Act: -0.1700
Data Index: 8310287 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3968. Min Act: -0.1700
Data Index: 3713608 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3968. Min Act: -0.1700
Data Index: 5393298 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3655. Min Act: -0.1700
Data Index: 5859515 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3343. Min Act: -0.1700
Data Index: 6950305 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3343. Min Act: -0.1700
Data Index: 4944915 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3655. Min Act: -0.1700
Data Index: 7964845 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3655. Min Act: -0.1700
Data Index: 5740616 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 7857798 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 6142486 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 1122179 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 1434692 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 5518022 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 3343903 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3343. Min Act: -0.1700
Data Index: 5110100 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 1938972 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 1246423 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 899744 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.2718. Min Act: -0.1700
Data Index: 3484443 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3968. Min Range: -5.3968
Max Act: 5.3030. Min Act: -0.1700
Data Index: 3188376 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19