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

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

Neuron 3733 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.9622. Min Act: -0.0000

Data Index: 393002 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1083289 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1163839 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6621. Min Act: 0.0000

Data Index: 1052040 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.7226. Min Act: -0.0000

Data Index: 523165 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1016624 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6835. Min Act: -0.0000

Data Index: 492895 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6985. Min Act: -0.0000

Data Index: 1233297 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6682. Min Act: -0.0000

Data Index: 596492 (C4 (Web Text))

Max Activating Token Index: 580

Text #9

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6644. Min Act: -0.0000

Data Index: 351465 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6502. Min Act: -0.0001

Data Index: 73211 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6375. Min Act: -0.0001

Data Index: 1041436 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6578. Min Act: 0.0000

Data Index: 86155 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6111. Min Act: -0.0000

Data Index: 155033 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6079. Min Act: -0.0000

Data Index: 716542 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5892. Min Act: -0.0000

Data Index: 740764 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5997. Min Act: -0.0000

Data Index: 269009 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6003. Min Act: -0.0000

Data Index: 704184 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.6388. Min Act: -0.0001

Data Index: 458484 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.9622. Min Range: -0.9622

Max Act: 0.5411. Min Act: -0.0000

Data Index: 206558 (C4 (Web Text))

Max Activating Token Index: 744