Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1314 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2883. Min Act: -0.0002

Data Index: 516692 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2583. Min Act: -0.0002

Data Index: 1224221 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2659. Min Act: -0.0002

Data Index: 1288097 (C4 (Web Text))

Max Activating Token Index: 61

Text #3

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2623. Min Act: -0.0002

Data Index: 720133 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2499. Min Act: -0.0002

Data Index: 1090042 (C4 (Web Text))

Max Activating Token Index: 26

Text #5

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2539. Min Act: -0.0002

Data Index: 4329 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2536. Min Act: -0.0002

Data Index: 1059971 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2635. Min Act: -0.0002

Data Index: 513554 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2542. Min Act: -0.0002

Data Index: 505795 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2484. Min Act: -0.0002

Data Index: 815437 (C4 (Web Text))

Max Activating Token Index: 490

Text #10

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2515. Min Act: -0.0002

Data Index: 1127000 (C4 (Web Text))

Max Activating Token Index: 88

Text #11

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2253. Min Act: -0.0002

Data Index: 956975 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2318. Min Act: -0.0002

Data Index: 300529 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2306. Min Act: -0.0002

Data Index: 511643 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2399. Min Act: -0.0002

Data Index: 951179 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2437. Min Act: -0.0002

Data Index: 1160613 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2449. Min Act: -0.0002

Data Index: 71002 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2330. Min Act: -0.0002

Data Index: 291329 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2439. Min Act: -0.0002

Data Index: 201225 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.2883. Min Range: -0.2883

Max Act: 0.2259. Min Act: -0.0002

Data Index: 393624 (C4 (Web Text))

Max Activating Token Index: 299