Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1083 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2430. Min Act: -0.1677
Data Index: 7598352 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2253. Min Act: -0.1700
Data Index: 1195401 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2253. Min Act: -0.1699
Data Index: 981988 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1685
Data Index: 170270 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2165. Min Act: -0.1693
Data Index: 4717140 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1693
Data Index: 5984365 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1696
Data Index: 8589859 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1699
Data Index: 1258069 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1700
Data Index: 2238220 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1700
Data Index: 7067678 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1693
Data Index: 8262861 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2165. Min Act: -0.1700
Data Index: 4675930 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.2077. Min Act: -0.1675
Data Index: 4717142 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.1989. Min Act: -0.1700
Data Index: 1128250 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.1901. Min Act: -0.1694
Data Index: 8186843 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.1989. Min Act: -0.1695
Data Index: 2651313 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.1989. Min Act: -0.1694
Data Index: 8117160 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.1989. Min Act: -0.1697
Data Index: 3180341 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.1989. Min Act: -0.1548
Data Index: 7622260 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2430. Min Range: -1.2430
Max Act: 1.1989. Min Act: -0.1700
Data Index: 1510397 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19