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

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

Neuron 631 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.8553. Min Act: -0.0000

Data Index: 1242397 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7926. Min Act: -0.0000

Data Index: 435323 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1337388 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7912. Min Act: -0.0000

Data Index: 278401 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7890. Min Act: -0.0000

Data Index: 675021 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7543. Min Act: -0.0000

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7307. Min Act: -0.0000

Data Index: 766008 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6541. Min Act: -0.0000

Data Index: 675402 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7549. Min Act: -0.0000

Data Index: 59272 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1157992 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1194629 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7115. Min Act: -0.0000

Data Index: 927040 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7064. Min Act: -0.0000

Data Index: 1333143 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6837. Min Act: -0.0000

Data Index: 602138 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6740. Min Act: -0.0000

Data Index: 342903 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6747. Min Act: -0.0000

Data Index: 94663 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6475. Min Act: -0.0000

Data Index: 254517 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.7098. Min Act: -0.0000

Data Index: 693304 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6620. Min Act: -0.0000

Data Index: 191026 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.8553. Min Range: -0.8553

Max Act: 0.6382. Min Act: -0.0000

Data Index: 974996 (C4 (Web Text))

Max Activating Token Index: 193