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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2454 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1549632 (Python Code)

Max Activating Token Index: 481

Text #1

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.6024. Min Act: -0.0000

Data Index: 561656 (C4 (Web Text))

Max Activating Token Index: 1022

Text #2

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.5504. Min Act: -0.0000

Data Index: 694510 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1128544 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1537203 (Python Code)

Max Activating Token Index: 151

Text #5

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1463678 (Python Code)

Max Activating Token Index: 246

Text #6

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4608. Min Act: -0.0000

Data Index: 51759 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4035. Min Act: -0.0000

Data Index: 179165 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1532741 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4125. Min Act: -0.0000

Data Index: 854957 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4744. Min Act: -0.0000

Data Index: 1571758 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1634182 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4608. Min Act: -0.0000

Data Index: 1379194 (Python Code)

Max Activating Token Index: 267

Text #13

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4295. Min Act: -0.0000

Data Index: 157955 (C4 (Web Text))

Max Activating Token Index: 864

Text #14

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1588385 (Python Code)

Max Activating Token Index: 567

Text #15

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4303. Min Act: -0.0000

Data Index: 643247 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4351. Min Act: -0.0000

Data Index: 627043 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4504. Min Act: -0.0000

Data Index: 70231 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.3868. Min Act: -0.0000

Data Index: 955261 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.6025. Min Range: -0.6025

Max Act: 0.4122. Min Act: -0.0000

Data Index: 852013 (C4 (Web Text))

Max Activating Token Index: 209