Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 956 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4567. Min Range: -6.4567
Max Act: 6.4567. Min Act: -0.1700
Data Index: 1960061 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4567. Min Range: -6.4567
Max Act: 6.0817. Min Act: -0.1700
Data Index: 8380029 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4567. Min Range: -6.4567
Max Act: 6.0817. Min Act: -0.1700
Data Index: 1196816 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.8942. Min Act: -0.1700
Data Index: 5154871 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.8004. Min Act: -0.1700
Data Index: 725100 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.8004. Min Act: -0.1700
Data Index: 1617511 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.7379. Min Act: -0.1700
Data Index: 3803462 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.7379. Min Act: -0.1700
Data Index: 3903683 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.8004. Min Act: -0.1700
Data Index: 6201979 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.7379. Min Act: -0.1700
Data Index: 5247584 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.7379. Min Act: -0.1700
Data Index: 886496 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.7067. Min Act: -0.1700
Data Index: 4595964 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.7379. Min Act: -0.1700
Data Index: 6992052 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.6754. Min Act: -0.1700
Data Index: 5340691 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.6442. Min Act: -0.1700
Data Index: 1381443 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.6442. Min Act: -0.1700
Data Index: 1266355 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.6129. Min Act: -0.1700
Data Index: 8100966 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.6442. Min Act: -0.1700
Data Index: 3430971 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.6129. Min Act: -0.1700
Data Index: 5796109 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4567. Min Range: -6.4567
Max Act: 5.5817. Min Act: -0.1700
Data Index: 5805711 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19