Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 536 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5708. Min Act: -0.1699
Data Index: 1464324 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5357. Min Act: -0.1699
Data Index: 6573780 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5445. Min Act: -0.1700
Data Index: 8321700 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5445. Min Act: -0.1700
Data Index: 4815532 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5445. Min Act: -0.1699
Data Index: 7414329 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5357. Min Act: -0.1700
Data Index: 4997567 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5445. Min Act: -0.1700
Data Index: 1599978 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5270. Min Act: -0.1700
Data Index: 2197176 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5357. Min Act: -0.1671
Data Index: 4952577 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5270. Min Act: -0.1700
Data Index: 6430808 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5182. Min Act: -0.1696
Data Index: 2071349 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5270. Min Act: -0.1700
Data Index: 4131222 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5182. Min Act: -0.1700
Data Index: 7015443 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5182. Min Act: -0.1700
Data Index: 8538146 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5182. Min Act: -0.1700
Data Index: 6618189 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5007. Min Act: -0.1700
Data Index: 4417414 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5182. Min Act: -0.1699
Data Index: 5412028 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5094. Min Act: -0.1699
Data Index: 7355021 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5182. Min Act: -0.1694
Data Index: 3475880 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5708. Min Range: -1.5708
Max Act: 1.5094. Min Act: -0.1698
Data Index: 5364209 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19