Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4330 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.9431. Min Act: -0.0000

Data Index: 1231415 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.7244. Min Act: -0.0000

Data Index: 565784 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6824. Min Act: -0.0000

Data Index: 86027 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6416. Min Act: -0.0000

Data Index: 439082 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6160. Min Act: -0.0000

Data Index: 838813 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1303553 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1321975 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5652. Min Act: -0.0000

Data Index: 1270255 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5689. Min Act: -0.0000

Data Index: 396648 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5824. Min Act: -0.0000

Data Index: 815799 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1081023 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5632. Min Act: 0.0000

Data Index: 769257 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5644. Min Act: -0.0000

Data Index: 270089 (C4 (Web Text))

Max Activating Token Index: 997

Text #13

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.6025. Min Act: -0.0000

Data Index: 1210262 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5304. Min Act: -0.0000

Data Index: 1094342 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5623. Min Act: -0.0000

Data Index: 382267 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5463. Min Act: -0.0000

Data Index: 1305791 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5760. Min Act: -0.0000

Data Index: 173840 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5723. Min Act: -0.0000

Data Index: 684800 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.9431. Min Range: -0.9431

Max Act: 0.5437. Min Act: 0.0000

Data Index: 1115177 (C4 (Web Text))

Max Activating Token Index: 86