Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2448 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.4727. Min Act: -0.1700
Data Index: 1994838 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.3164. Min Act: -0.1700
Data Index: 2690664 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.1914. Min Act: -0.1700
Data Index: 3899187 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.1602. Min Act: -0.1700
Data Index: 174902 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.1289. Min Act: -0.1700
Data Index: 8074344 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.1289. Min Act: -0.1700
Data Index: 8069596 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.0977. Min Act: -0.1700
Data Index: 1349711 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.0977. Min Act: -0.1700
Data Index: 7754844 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.0664. Min Act: -0.1700
Data Index: 5335567 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.0352. Min Act: -0.1700
Data Index: 7769179 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4727. Min Range: -6.4727
Max Act: 6.0039. Min Act: -0.1700
Data Index: 4179204 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 563823 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9727. Min Act: -0.1700
Data Index: 89459 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 2438708 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 2531247 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 3075506 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 3273754 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 1473695 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 5136738 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4727. Min Range: -6.4727
Max Act: 5.9414. Min Act: -0.1700
Data Index: 5894957 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19