Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4185 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 7.7341. Min Range: -7.7341

Max Act: 7.7341. Min Act: -0.0000

Data Index: 1838680 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.9176. Min Act: -0.0000

Data Index: 1573846 (The Pile)

Max Activating Token Index: 12

Text #2

Max Range: 7.7341. Min Range: -7.7341

Max Act: 7.4064. Min Act: -0.0000

Data Index: 172142 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.9938. Min Act: -0.0000

Data Index: 869559 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 7.7341. Min Range: -7.7341

Max Act: 7.0634. Min Act: -0.0000

Data Index: 1105377 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 7.7341. Min Range: -7.7341

Max Act: 7.4288. Min Act: -0.0000

Data Index: 1223 (The Pile)

Max Activating Token Index: 11

Text #6

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.9040. Min Act: -0.0000

Data Index: 1161802 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.9178. Min Act: -0.0000

Data Index: 1168831 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.7010. Min Act: -0.0000

Data Index: 1374988 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.6709. Min Act: -0.0000

Data Index: 1451302 (The Pile)

Max Activating Token Index: 567

Text #10

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.6211. Min Act: -0.0000

Data Index: 745224 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.5184. Min Act: -0.0000

Data Index: 1672048 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.6927. Min Act: -0.0000

Data Index: 843803 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.5269. Min Act: -0.0000

Data Index: 261962 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.8556. Min Act: -0.0000

Data Index: 1858398 (The Pile)

Max Activating Token Index: 175

Text #15

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.4363. Min Act: -0.0000

Data Index: 1623229 (The Pile)

Max Activating Token Index: 609

Text #16

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.2926. Min Act: -0.0000

Data Index: 1992206 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.6211. Min Act: -0.0000

Data Index: 153017 (The Pile)

Max Activating Token Index: 968

Text #18

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.4770. Min Act: -0.0000

Data Index: 470112 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 7.7341. Min Range: -7.7341

Max Act: 6.7501. Min Act: -0.0000

Data Index: 1017379 (The Pile)

Max Activating Token Index: 700