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

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

Neuron 754 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3526. Min Range: -2.3526

Max Act: 2.3526. Min Act: -0.0000

Data Index: 531364 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.7380. Min Act: -0.0000

Data Index: 496671 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.6216. Min Act: -0.0001

Data Index: 160007 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1237140 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.7398. Min Act: -0.0001

Data Index: 455746 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.6033. Min Act: -0.0000

Data Index: 558635 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.5669. Min Act: -0.0001

Data Index: 715209 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.6156. Min Act: -0.0000

Data Index: 5206 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.6591. Min Act: -0.0000

Data Index: 1326378 (C4 (Web Text))

Max Activating Token Index: 131

Text #9

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.6074. Min Act: -0.0001

Data Index: 807812 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.5650. Min Act: -0.0001

Data Index: 798478 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.3792. Min Act: -0.0001

Data Index: 949246 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.3934. Min Act: -0.0000

Data Index: 548442 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.4126. Min Act: -0.0000

Data Index: 389566 (C4 (Web Text))

Max Activating Token Index: 785

Text #14

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.5356. Min Act: -0.0001

Data Index: 331118 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.3487. Min Act: -0.0000

Data Index: 360369 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.4772. Min Act: -0.0001

Data Index: 551941 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.4500. Min Act: -0.0001

Data Index: 243945 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.5109. Min Act: -0.0001

Data Index: 907262 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 2.3526. Min Range: -2.3526

Max Act: 1.4956. Min Act: -0.0001

Data Index: 56522 (C4 (Web Text))

Max Activating Token Index: 580