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

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

Neuron 771 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1968. Min Act: -0.0001

Data Index: 1076177 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1235857 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1663. Min Act: -0.0001

Data Index: 804045 (C4 (Web Text))

Max Activating Token Index: 401

Text #3

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1551. Min Act: -0.0001

Data Index: 341318 (C4 (Web Text))

Max Activating Token Index: 1007

Text #4

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1604. Min Act: -0.0001

Data Index: 730593 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1561. Min Act: -0.0001

Data Index: 372030 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1413. Min Act: -0.0001

Data Index: 279521 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1570. Min Act: -0.0001

Data Index: 116342 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1329. Min Act: -0.0001

Data Index: 839667 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1141585 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1329. Min Act: -0.0001

Data Index: 773379 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1378. Min Act: -0.0001

Data Index: 182465 (C4 (Web Text))

Max Activating Token Index: 164

Text #12

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1355183 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1445. Min Act: -0.0001

Data Index: 888596 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1278319 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1412. Min Act: -0.0001

Data Index: 757358 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1397. Min Act: -0.0001

Data Index: 1195983 (C4 (Web Text))

Max Activating Token Index: 192

Text #17

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1404. Min Act: -0.0001

Data Index: 73377 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1162. Min Act: -0.0001

Data Index: 493195 (C4 (Web Text))

Max Activating Token Index: 206

Text #19

Max Range: 0.1968. Min Range: -0.1968

Max Act: 0.1472. Min Act: -0.0001

Data Index: 948702 (C4 (Web Text))

Max Activating Token Index: 577