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

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

Neuron 1758 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: 3.4337. Min Range: -3.4337

Max Act: 3.4337. Min Act: -0.0001

Data Index: 1319767 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.8611. Min Act: -0.0001

Data Index: 305163 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.8241. Min Act: -0.0001

Data Index: 680610 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.8838. Min Act: -0.0001

Data Index: 162449 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.6607. Min Act: -0.0001

Data Index: 1337682 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.7148. Min Act: -0.0001

Data Index: 915509 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.5712. Min Act: -0.0001

Data Index: 1347605 (C4 (Web Text))

Max Activating Token Index: 304

Text #7

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.5500. Min Act: -0.0001

Data Index: 766904 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.5359. Min Act: -0.0000

Data Index: 454349 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.5936. Min Act: -0.0001

Data Index: 839286 (C4 (Web Text))

Max Activating Token Index: 392

Text #10

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.5144. Min Act: -0.0000

Data Index: 1122266 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.4979. Min Act: -0.0001

Data Index: 694966 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.2805. Min Act: -0.0000

Data Index: 952903 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.4445. Min Act: -0.0000

Data Index: 914814 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.4530. Min Act: -0.0001

Data Index: 13475 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.4367. Min Act: -0.0001

Data Index: 1265858 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.2146. Min Act: -0.0000

Data Index: 1006323 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.3190. Min Act: -0.0001

Data Index: 858548 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.3511. Min Act: -0.0000

Data Index: 345322 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 3.4337. Min Range: -3.4337

Max Act: 2.2705. Min Act: -0.0000

Data Index: 544906 (C4 (Web Text))

Max Activating Token Index: 908