Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3179 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5514. Min Range: -6.5514
Max Act: 6.5514. Min Act: -0.1700
Data Index: 3658809 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5514. Min Range: -6.5514
Max Act: 6.1764. Min Act: -0.1700
Data Index: 1493361 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5514. Min Range: -6.5514
Max Act: 6.0514. Min Act: -0.1700
Data Index: 2328498 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5514. Min Range: -6.5514
Max Act: 6.0514. Min Act: -0.1700
Data Index: 7774075 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.9889. Min Act: -0.1700
Data Index: 3526092 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5514. Min Range: -6.5514
Max Act: 6.0202. Min Act: -0.1700
Data Index: 6550513 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5514. Min Range: -6.5514
Max Act: 6.0202. Min Act: -0.1700
Data Index: 1336170 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.9577. Min Act: -0.1700
Data Index: 7418486 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.9264. Min Act: -0.1700
Data Index: 1252401 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.8952. Min Act: -0.1700
Data Index: 8226110 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.8952. Min Act: -0.1700
Data Index: 5075426 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.8327. Min Act: -0.1700
Data Index: 2180575 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.8014. Min Act: -0.1700
Data Index: 307958 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.8014. Min Act: -0.1700
Data Index: 440490 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.7702. Min Act: -0.1700
Data Index: 2604 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.7702. Min Act: -0.1700
Data Index: 699341 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.7702. Min Act: -0.1700
Data Index: 4032620 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.8014. Min Act: -0.1700
Data Index: 3034667 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.7702. Min Act: -0.1700
Data Index: 5606161 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5514. Min Range: -6.5514
Max Act: 5.7702. Min Act: -0.1700
Data Index: 6500167 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19