Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 934 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.4147. Min Act: -0.0001
Data Index: 1738927 (The Pile)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.4034. Min Act: -0.0001
Data Index: 1463153 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3733. Min Act: -0.0001
Data Index: 1859498 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3504. Min Act: -0.0001
Data Index: 1763763 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3914. Min Act: -0.0001
Data Index: 1284696 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3621. Min Act: -0.0001
Data Index: 915066 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3411. Min Act: -0.0001
Data Index: 1793814 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3528. Min Act: -0.0001
Data Index: 372352 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3615. Min Act: -0.0001
Data Index: 270947 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3654. Min Act: -0.0001
Data Index: 58286 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3467. Min Act: -0.0001
Data Index: 267150 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3323. Min Act: -0.0001
Data Index: 1633832 (The Pile)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3412. Min Act: -0.0001
Data Index: 1852033 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3378. Min Act: -0.0001
Data Index: 999319 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3254. Min Act: -0.0001
Data Index: 328712 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3362. Min Act: -0.0001
Data Index: 1870470 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3296. Min Act: -0.0001
Data Index: 640939 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3215. Min Act: -0.0001
Data Index: 547566 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3205. Min Act: -0.0001
Data Index: 1776101 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4147. Min Range: -0.4147
Max Act: 0.3300. Min Act: -0.0001
Data Index: 238819 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #19