Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1424 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.2560. Min Act: -0.1700
Data Index: 8752705 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.2560. Min Act: -0.1700
Data Index: 301727 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.2246. Min Act: -0.1700
Data Index: 3353911 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.2246. Min Act: -0.1700
Data Index: 911531 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.2089. Min Act: -0.1700
Data Index: 3936301 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.2089. Min Act: -0.1700
Data Index: 8596134 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1931. Min Act: -0.1700
Data Index: 5558519 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1774. Min Act: -0.1700
Data Index: 7749842 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1931. Min Act: -0.1700
Data Index: 4383430 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1459. Min Act: -0.1700
Data Index: 1947082 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1774. Min Act: -0.1700
Data Index: 8585426 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1617. Min Act: -0.1700
Data Index: 6871656 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1617. Min Act: -0.1700
Data Index: 4615402 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1617. Min Act: -0.1700
Data Index: 3613033 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1617. Min Act: -0.1700
Data Index: 4686424 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1617. Min Act: -0.1700
Data Index: 5598996 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1459. Min Act: -0.1700
Data Index: 1812063 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1774. Min Act: -0.1700
Data Index: 7430711 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1459. Min Act: -0.1700
Data Index: 1346008 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2560. Min Range: -3.2560
Max Act: 3.1774. Min Act: -0.1700
Data Index: 3840136 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19