Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3573 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1302. Min Range: -2.1302

Max Act: 2.0374. Min Act: -0.0001

Data Index: 804853 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 2.1302. Min Range: -2.1302

Max Act: 2.1302. Min Act: -0.0001

Data Index: 769988 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.7292. Min Act: -0.0000

Data Index: 444701 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.8426. Min Act: -0.0001

Data Index: 484621 (C4 (Web Text))

Max Activating Token Index: 792

Text #4

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.7545. Min Act: -0.0000

Data Index: 989038 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.8886. Min Act: -0.0001

Data Index: 985595 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.7822. Min Act: -0.0000

Data Index: 205231 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.6775. Min Act: -0.0000

Data Index: 445953 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.4741. Min Act: -0.0001

Data Index: 817541 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.5898. Min Act: -0.0000

Data Index: 870816 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.5219. Min Act: -0.0000

Data Index: 1246701 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.5201. Min Act: -0.0001

Data Index: 605494 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.3631. Min Act: -0.0000

Data Index: 850089 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.4287. Min Act: -0.0001

Data Index: 1133020 (C4 (Web Text))

Max Activating Token Index: 928

Text #14

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.5093. Min Act: -0.0000

Data Index: 478052 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.4663. Min Act: -0.0000

Data Index: 1039409 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.2931. Min Act: -0.0000

Data Index: 303091 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.3399. Min Act: -0.0001

Data Index: 657754 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.3244. Min Act: -0.0000

Data Index: 275512 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 2.1302. Min Range: -2.1302

Max Act: 1.2715. Min Act: -0.0000

Data Index: 88249 (C4 (Web Text))

Max Activating Token Index: 121