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

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

Neuron 3423 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.3635. Min Act: -0.0000

Data Index: 1027950 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2815. Min Act: -0.0000

Data Index: 218603 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1280232 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2666. Min Act: -0.0001

Data Index: 722848 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2830. Min Act: -0.0001

Data Index: 35556 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2708. Min Act: -0.0001

Data Index: 1248626 (C4 (Web Text))

Max Activating Token Index: 867

Text #6

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2495. Min Act: -0.0001

Data Index: 840119 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2526. Min Act: -0.0001

Data Index: 439261 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2609. Min Act: -0.0000

Data Index: 248354 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2606. Min Act: -0.0001

Data Index: 616768 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2498. Min Act: -0.0000

Data Index: 688779 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2393. Min Act: -0.0001

Data Index: 22532 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2573. Min Act: -0.0000

Data Index: 377417 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2555. Min Act: -0.0000

Data Index: 206377 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2488. Min Act: -0.0001

Data Index: 579262 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1347178 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2532. Min Act: -0.0001

Data Index: 992594 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2527. Min Act: -0.0001

Data Index: 809393 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2521. Min Act: -0.0001

Data Index: 1207497 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 0.3635. Min Range: -0.3635

Max Act: 0.2505. Min Act: -0.0001

Data Index: 1329918 (C4 (Web Text))

Max Activating Token Index: 127