Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 429 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0149. Min Range: -1.0149

Max Act: 1.0149. Min Act: -0.0000

Data Index: 884107 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8973. Min Act: -0.0001

Data Index: 1586737 (Python Code)

Max Activating Token Index: 638

Text #2

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8826. Min Act: -0.0000

Data Index: 219043 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8788. Min Act: -0.0001

Data Index: 312492 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8111. Min Act: -0.0000

Data Index: 257492 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8576. Min Act: -0.0001

Data Index: 1387913 (Python Code)

Max Activating Token Index: 508

Text #6

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8236. Min Act: -0.0001

Data Index: 594505 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7835. Min Act: -0.0001

Data Index: 1504478 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1517308 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8231. Min Act: -0.0001

Data Index: 1076050 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7941. Min Act: -0.0001

Data Index: 375872 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8104. Min Act: -0.0000

Data Index: 1128674 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7674. Min Act: -0.0000

Data Index: 112894 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7589. Min Act: -0.0000

Data Index: 936729 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7557. Min Act: -0.0001

Data Index: 1531561 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1136599 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7812. Min Act: -0.0001

Data Index: 1381839 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.8006. Min Act: -0.0001

Data Index: 1611385 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7391. Min Act: -0.0001

Data Index: 538933 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 1.0149. Min Range: -1.0149

Max Act: 0.7118. Min Act: -0.0000

Data Index: 208644 (C4 (Web Text))

Max Activating Token Index: 1002