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

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

Neuron 24 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.1136. Min Act: -0.0001

Data Index: 633987 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.1454. Min Act: -0.0001

Data Index: 1314658 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.1094. Min Act: -0.0001

Data Index: 913299 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0193. Min Act: -0.0001

Data Index: 1024763 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0460. Min Act: -0.0001

Data Index: 1311773 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0480. Min Act: -0.0001

Data Index: 567917 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0839. Min Act: -0.0001

Data Index: 584996 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0660. Min Act: -0.0001

Data Index: 802099 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.1357. Min Act: -0.0001

Data Index: 1131723 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0504. Min Act: -0.0001

Data Index: 1267050 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0171. Min Act: -0.0001

Data Index: 46944 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0184. Min Act: -0.0001

Data Index: 1318839 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 1.1454. Min Range: -1.1454

Max Act: 0.9613. Min Act: -0.0000

Data Index: 357880 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.1454. Min Range: -1.1454

Max Act: 0.9838. Min Act: -0.0001

Data Index: 640150 (C4 (Web Text))

Max Activating Token Index: 386

Text #14

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0088. Min Act: -0.0001

Data Index: 1222234 (C4 (Web Text))

Max Activating Token Index: 324

Text #15

Max Range: 1.1454. Min Range: -1.1454

Max Act: 1.0121. Min Act: -0.0001

Data Index: 859203 (C4 (Web Text))

Max Activating Token Index: 135

Text #16

Max Range: 1.1454. Min Range: -1.1454

Max Act: 0.9818. Min Act: -0.0001

Data Index: 1313206 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 1.1454. Min Range: -1.1454

Max Act: 0.9622. Min Act: -0.0001

Data Index: 1178659 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 1.1454. Min Range: -1.1454

Max Act: 0.9341. Min Act: -0.0001

Data Index: 222096 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.1454. Min Range: -1.1454

Max Act: 0.9875. Min Act: -0.0001

Data Index: 435672 (C4 (Web Text))

Max Activating Token Index: 109