Model: None
Dataset: The Pile
Neuron 845 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.6072. Min Act: -0.1700
Data Index: 1057554 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.6229. Min Act: -0.1700
Data Index: 8244975 (The Pile)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5759. Min Act: -0.1700
Data Index: 8001449 (The Pile)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.6072. Min Act: -0.1700
Data Index: 1586825 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5916. Min Act: -0.1700
Data Index: 10700821 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.3251. Min Act: -0.1700
Data Index: 7242813 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.4819. Min Act: -0.1699
Data Index: 2388670 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5289. Min Act: -0.1700
Data Index: 7536588 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.4819. Min Act: -0.1700
Data Index: 5229181 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5603. Min Act: -0.1700
Data Index: 9011650 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5603. Min Act: -0.1700
Data Index: 5743328 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.4976. Min Act: -0.1700
Data Index: 3604009 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5603. Min Act: -0.1700
Data Index: 6642267 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5916. Min Act: -0.1700
Data Index: 307211 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.4976. Min Act: -0.1700
Data Index: 9132617 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5446. Min Act: -0.1700
Data Index: 8257251 (The Pile)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.4192. Min Act: -0.1700
Data Index: 4099500 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.4192. Min Act: -0.1700
Data Index: 7641667 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.4506. Min Act: -0.1700
Data Index: 5247537 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6229. Min Range: -3.6229
Max Act: 3.5289. Min Act: -0.1700
Data Index: 2571456 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19