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

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

Neuron 1615 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.3399. Min Act: -0.0000

Data Index: 37237 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2642. Min Act: -0.0000

Data Index: 630685 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2619. Min Act: -0.0001

Data Index: 1275756 (C4 (Web Text))

Max Activating Token Index: 786

Text #3

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2670. Min Act: -0.0001

Data Index: 737356 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2524. Min Act: -0.0000

Data Index: 897322 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2629. Min Act: -0.0000

Data Index: 86535 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2778. Min Act: -0.0001

Data Index: 1241942 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2859. Min Act: -0.0000

Data Index: 805263 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2572. Min Act: -0.0000

Data Index: 484748 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2789. Min Act: -0.0001

Data Index: 257713 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2363. Min Act: -0.0001

Data Index: 228629 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1101867 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2561. Min Act: -0.0001

Data Index: 809931 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2970. Min Act: -0.0001

Data Index: 466407 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2408. Min Act: -0.0000

Data Index: 462541 (C4 (Web Text))

Max Activating Token Index: 217

Text #15

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2218. Min Act: -0.0000

Data Index: 126127 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2299. Min Act: -0.0000

Data Index: 1317026 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2357. Min Act: -0.0001

Data Index: 523283 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2412. Min Act: -0.0000

Data Index: 271295 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.3399. Min Range: -0.3399

Max Act: 0.2102. Min Act: -0.0000

Data Index: 399892 (C4 (Web Text))

Max Activating Token Index: 208