Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2358 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.6740. Min Act: -0.1700
Data Index: 5229900 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.5694. Min Act: -0.1700
Data Index: 1886424 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.5519. Min Act: -0.1699
Data Index: 2437497 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.5432. Min Act: -0.1700
Data Index: 6208451 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.5256. Min Act: -0.1700
Data Index: 6037890 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.5169. Min Act: -0.1700
Data Index: 3385644 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.5169. Min Act: -0.1700
Data Index: 8064830 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4993. Min Act: -0.1700
Data Index: 6279812 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4817. Min Act: -0.1700
Data Index: 5967867 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4993. Min Act: -0.1700
Data Index: 1966337 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4905. Min Act: -0.1700
Data Index: 4369491 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4730. Min Act: -0.1700
Data Index: 5229899 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4642. Min Act: -0.1700
Data Index: 8672495 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4905. Min Act: -0.1700
Data Index: 8064829 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4730. Min Act: -0.1700
Data Index: 1109772 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4730. Min Act: -0.1700
Data Index: 4563967 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4730. Min Act: -0.1700
Data Index: 5172275 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4730. Min Act: -0.1697
Data Index: 993534 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4554. Min Act: -0.1700
Data Index: 6841785 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6740. Min Range: -1.6740
Max Act: 1.4642. Min Act: -0.1700
Data Index: 1750210 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19