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

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

Neuron 1665 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0001

Data Index: 988907 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1540. Min Act: -0.0001

Data Index: 794928 (C4 (Web Text))

Max Activating Token Index: 377

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1521. Min Act: -0.0001

Data Index: 714381 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1159946 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1494. Min Act: -0.0001

Data Index: 949633 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1116697 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1369. Min Act: -0.0001

Data Index: 312550 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1447. Min Act: -0.0001

Data Index: 54840 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1404. Min Act: -0.0001

Data Index: 933356 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1508. Min Act: -0.0001

Data Index: 687267 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1330. Min Act: -0.0001

Data Index: 587091 (C4 (Web Text))

Max Activating Token Index: 596

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1252. Min Act: -0.0001

Data Index: 331250 (C4 (Web Text))

Max Activating Token Index: 631

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1361. Min Act: -0.0001

Data Index: 662766 (C4 (Web Text))

Max Activating Token Index: 630

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1142493 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1320. Min Act: -0.0001

Data Index: 49997 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1282. Min Act: -0.0001

Data Index: 137799 (C4 (Web Text))

Max Activating Token Index: 201

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1275. Min Act: -0.0001

Data Index: 152741 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1234. Min Act: -0.0001

Data Index: 459010 (C4 (Web Text))

Max Activating Token Index: 209

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1173. Min Act: -0.0001

Data Index: 723778 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1164. Min Act: -0.0001

Data Index: 830697 (C4 (Web Text))

Max Activating Token Index: 524