Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2046 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.7492. Min Act: -0.1700
Data Index: 5473300 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.7805. Min Act: -0.1700
Data Index: 6258869 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.7179. Min Act: -0.1700
Data Index: 5473301 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.7023. Min Act: -0.1700
Data Index: 38023 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6866. Min Act: -0.1700
Data Index: 5722180 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6866. Min Act: -0.1700
Data Index: 8296521 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6710. Min Act: -0.1700
Data Index: 4727711 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 3018422 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 5330636 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 1897726 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 8572272 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 3121797 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6553. Min Act: -0.1700
Data Index: 6531931 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 7815538 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6710. Min Act: -0.1700
Data Index: 7708671 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 6073271 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 3908629 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6397. Min Act: -0.1700
Data Index: 2364587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6553. Min Act: -0.1700
Data Index: 8504612 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7805. Min Range: -3.7805
Max Act: 3.6553. Min Act: -0.1700
Data Index: 8469973 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19