Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0987. Min Act: -0.1700
Data Index: 4993226 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0725. Min Act: -0.1700
Data Index: 4414941 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0812. Min Act: -0.1700
Data Index: 4993228 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0812. Min Act: -0.1700
Data Index: 3340857 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0725. Min Act: -0.1699
Data Index: 5350345 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0463. Min Act: -0.1700
Data Index: 8376824 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0463. Min Act: -0.1700
Data Index: 2332641 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0376. Min Act: -0.1700
Data Index: 3496025 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0550. Min Act: -0.1696
Data Index: 3384663 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0376. Min Act: -0.1700
Data Index: 4563063 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0463. Min Act: -0.1699
Data Index: 4648144 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0289. Min Act: -0.1699
Data Index: 953761 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0289. Min Act: -0.1700
Data Index: 8193584 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0289. Min Act: -0.1700
Data Index: 583710 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0376. Min Act: -0.1700
Data Index: 583712 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0289. Min Act: -0.1700
Data Index: 7878011 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0202. Min Act: -0.1700
Data Index: 8794604 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0202. Min Act: -0.1700
Data Index: 3031034 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0202. Min Act: -0.1700
Data Index: 7982229 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0987. Min Range: -1.0987
Max Act: 1.0115. Min Act: -0.1700
Data Index: 4993232 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19