Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4704 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.1374. Min Act: -0.1700
Data Index: 645857 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0436. Min Act: -0.1700
Data Index: 7926783 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0436. Min Act: -0.1700
Data Index: 7944457 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1374. Min Range: -4.1374
Max Act: 4.0436. Min Act: -0.1700
Data Index: 6955124 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9811. Min Act: -0.1700
Data Index: 4220326 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.9811. Min Act: -0.1700
Data Index: 396185 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.8873. Min Act: -0.1700
Data Index: 2080738 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.8873. Min Act: -0.1700
Data Index: 8618607 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.8560. Min Act: -0.1700
Data Index: 1185855 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.8560. Min Act: -0.1700
Data Index: 2039869 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.8560. Min Act: -0.1700
Data Index: 6512741 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.8247. Min Act: -0.1700
Data Index: 438841 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7622. Min Act: -0.1700
Data Index: 1356252 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7935. Min Act: -0.1700
Data Index: 1963343 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7778. Min Act: -0.1700
Data Index: 4988219 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7309. Min Act: -0.1700
Data Index: 8305645 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7309. Min Act: -0.1700
Data Index: 2824176 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7309. Min Act: -0.1700
Data Index: 6368146 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7153. Min Act: -0.1700
Data Index: 3859047 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1374. Min Range: -4.1374
Max Act: 3.7153. Min Act: -0.1700
Data Index: 5100378 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19