Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 40 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0749. Min Act: -0.0003

Data Index: 1149561 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0555. Min Act: -0.0003

Data Index: 332393 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0519. Min Act: -0.0003

Data Index: 901770 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0539. Min Act: -0.0003

Data Index: 231035 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0481. Min Act: -0.0004

Data Index: 481034 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0494. Min Act: -0.0003

Data Index: 1263236 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0520. Min Act: -0.0003

Data Index: 444982 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0511. Min Act: -0.0004

Data Index: 198944 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0482. Min Act: -0.0004

Data Index: 1140818 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1136234 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0481. Min Act: -0.0003

Data Index: 729990 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1216153 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0506. Min Act: -0.0003

Data Index: 605001 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1040049 (C4 (Web Text))

Max Activating Token Index: 545

Text #14

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1104646 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0472. Min Act: -0.0003

Data Index: 477436 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0468. Min Act: -0.0003

Data Index: 1456 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0481. Min Act: -0.0003

Data Index: 438627 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0475. Min Act: -0.0003

Data Index: 311797 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 0.0749. Min Range: -0.0749

Max Act: 0.0445. Min Act: -0.0004

Data Index: 726379 (C4 (Web Text))

Max Activating Token Index: 357