Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 31 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.2275. Min Act: -0.0001

Data Index: 937116 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.2245. Min Act: -0.0001

Data Index: 865585 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1939. Min Act: -0.0001

Data Index: 451398 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1684. Min Act: -0.0001

Data Index: 114182 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1696. Min Act: -0.0001

Data Index: 783196 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1104412 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1607. Min Act: -0.0001

Data Index: 185853 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1693. Min Act: -0.0001

Data Index: 1170677 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1509. Min Act: -0.0001

Data Index: 58798 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1587. Min Act: -0.0001

Data Index: 656401 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1082743 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1435. Min Act: -0.0001

Data Index: 8558 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1532. Min Act: -0.0001

Data Index: 977781 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1414. Min Act: -0.0001

Data Index: 836020 (C4 (Web Text))

Max Activating Token Index: 536

Text #14

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1225472 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1404. Min Act: -0.0001

Data Index: 600771 (C4 (Web Text))

Max Activating Token Index: 173

Text #16

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1350. Min Act: -0.0001

Data Index: 819326 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1431. Min Act: -0.0001

Data Index: 952306 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1464. Min Act: -0.0001

Data Index: 685894 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.2275. Min Range: -0.2275

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1049705 (C4 (Web Text))

Max Activating Token Index: 869