Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1203 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.3707. Min Act: -0.0001

Data Index: 1263736 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.3531. Min Act: -0.0001

Data Index: 914574 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.3335. Min Act: -0.0001

Data Index: 299404 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.3417. Min Act: -0.0001

Data Index: 1359422 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.3171. Min Act: -0.0001

Data Index: 1257278 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.3049. Min Act: -0.0001

Data Index: 1011292 (C4 (Web Text))

Max Activating Token Index: 245

Text #6

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.3178. Min Act: -0.0001

Data Index: 936929 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2734. Min Act: -0.0001

Data Index: 465427 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2854. Min Act: -0.0001

Data Index: 1265812 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2835. Min Act: -0.0001

Data Index: 510548 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2822. Min Act: -0.0001

Data Index: 809209 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1351256 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2553. Min Act: -0.0001

Data Index: 400478 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2609. Min Act: -0.0001

Data Index: 605973 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2562. Min Act: -0.0001

Data Index: 1174663 (C4 (Web Text))

Max Activating Token Index: 702

Text #15

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2438. Min Act: -0.0001

Data Index: 988276 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2555. Min Act: -0.0001

Data Index: 603997 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2543. Min Act: -0.0001

Data Index: 670943 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2599. Min Act: -0.0001

Data Index: 540228 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.3707. Min Range: -0.3707

Max Act: 0.2419. Min Act: -0.0001

Data Index: 1052654 (C4 (Web Text))

Max Activating Token Index: 563