Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2712 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.9208. Min Act: -0.1700
Data Index: 5353486 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8867. Min Act: -0.1700
Data Index: 4470882 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8525. Min Act: -0.1700
Data Index: 8427523 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8525. Min Act: -0.1700
Data Index: 8326705 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8525. Min Act: -0.1700
Data Index: 43094 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8525. Min Act: -0.1700
Data Index: 3639179 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8353. Min Act: -0.1700
Data Index: 7199681 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8353. Min Act: -0.1700
Data Index: 8207926 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8353. Min Act: -0.1700
Data Index: 4438335 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8353. Min Act: -0.1700
Data Index: 2276195 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8353. Min Act: -0.1700
Data Index: 627028 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8182. Min Act: -0.1699
Data Index: 4865870 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8182. Min Act: -0.1698
Data Index: 3539085 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8182. Min Act: -0.1700
Data Index: 4642212 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8182. Min Act: -0.1700
Data Index: 7041627 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8182. Min Act: -0.1700
Data Index: 349445 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8096. Min Act: -0.1700
Data Index: 781475 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8182. Min Act: -0.1700
Data Index: 4174432 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8182. Min Act: -0.1697
Data Index: 1895768 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9208. Min Range: -1.9208
Max Act: 1.8096. Min Act: -0.1700
Data Index: 6118737 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19