Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.5377. Min Act: -0.1698
Data Index: 5659345 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.5290. Min Act: -0.1700
Data Index: 2878757 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.5202. Min Act: -0.1698
Data Index: 7591609 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4939. Min Act: -0.1700
Data Index: 5412506 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4939. Min Act: -0.1700
Data Index: 8633472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4675. Min Act: -0.1697
Data Index: 1066106 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4587. Min Act: -0.1700
Data Index: 904376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4587. Min Act: -0.1700
Data Index: 6931641 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4499. Min Act: -0.1700
Data Index: 1859560 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4411. Min Act: -0.1692
Data Index: 8712354 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4411. Min Act: -0.1698
Data Index: 952995 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4411. Min Act: -0.1699
Data Index: 6440393 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4323. Min Act: -0.1700
Data Index: 1165162 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4235. Min Act: -0.1700
Data Index: 1864102 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4147. Min Act: -0.1685
Data Index: 5608746 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4059. Min Act: -0.1700
Data Index: 8453393 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4147. Min Act: -0.1697
Data Index: 4270455 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4147. Min Act: -0.1700
Data Index: 726211 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4147. Min Act: -0.1695
Data Index: 3602962 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5377. Min Range: -1.5377
Max Act: 1.4059. Min Act: -0.1700
Data Index: 6350170 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19