Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1730 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8765. Min Act: -0.1698
Data Index: 62319 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8337. Min Act: -0.1700
Data Index: 8155060 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8423. Min Act: -0.1700
Data Index: 8395602 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8165. Min Act: -0.1700
Data Index: 529104 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8165. Min Act: -0.1699
Data Index: 1780137 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8079. Min Act: -0.1697
Data Index: 4414188 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8079. Min Act: -0.1699
Data Index: 6464469 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7907. Min Act: -0.1700
Data Index: 5462641 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7907. Min Act: -0.1694
Data Index: 6315559 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7907. Min Act: -0.1697
Data Index: 5869171 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.8079. Min Act: -0.1698
Data Index: 5869172 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7821. Min Act: -0.1693
Data Index: 903415 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7649. Min Act: -0.1700
Data Index: 548264 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7649. Min Act: -0.1700
Data Index: 7229293 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7649. Min Act: -0.1700
Data Index: 3914303 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7562. Min Act: -0.1700
Data Index: 5299496 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7562. Min Act: -0.1676
Data Index: 2083110 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7562. Min Act: -0.1688
Data Index: 312200 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7562. Min Act: -0.1700
Data Index: 5463030 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8765. Min Range: -1.8765
Max Act: 1.7562. Min Act: -0.1700
Data Index: 6315560 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19