Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3453 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1985. Min Act: -0.0001

Data Index: 1220445 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1917. Min Act: -0.0000

Data Index: 66425 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1676. Min Act: -0.0000

Data Index: 620658 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1619. Min Act: -0.0001

Data Index: 318705 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1620. Min Act: -0.0001

Data Index: 655758 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1527. Min Act: -0.0001

Data Index: 991870 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1500. Min Act: -0.0000

Data Index: 434049 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1516. Min Act: -0.0001

Data Index: 713315 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1445. Min Act: -0.0001

Data Index: 138873 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1277484 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1203105 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1464. Min Act: -0.0001

Data Index: 342075 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1354. Min Act: -0.0001

Data Index: 1185176 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1384. Min Act: -0.0000

Data Index: 116775 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1368. Min Act: -0.0001

Data Index: 440327 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1221621 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1312. Min Act: -0.0001

Data Index: 2800 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1312594 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1256086 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1386. Min Act: -0.0001

Data Index: 935579 (C4 (Web Text))

Max Activating Token Index: 675