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

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

Neuron 2503 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3440. Min Act: -0.0001

Data Index: 545012 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3177. Min Act: -0.0001

Data Index: 1111737 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.3095. Min Act: -0.0001

Data Index: 226178 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1154259 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2799. Min Act: -0.0001

Data Index: 246953 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2788. Min Act: -0.0001

Data Index: 472772 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2618. Min Act: -0.0001

Data Index: 852399 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2700. Min Act: -0.0001

Data Index: 494704 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2742. Min Act: -0.0001

Data Index: 161173 (C4 (Web Text))

Max Activating Token Index: 742

Text #9

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2550. Min Act: -0.0001

Data Index: 158706 (C4 (Web Text))

Max Activating Token Index: 569

Text #10

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2621. Min Act: -0.0001

Data Index: 557433 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2612. Min Act: -0.0001

Data Index: 1302138 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2561. Min Act: -0.0001

Data Index: 64887 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2570. Min Act: -0.0001

Data Index: 1195997 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1061397 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2532. Min Act: -0.0001

Data Index: 664976 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2352. Min Act: -0.0001

Data Index: 905794 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2507. Min Act: -0.0001

Data Index: 61734 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1296933 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.3440. Min Range: -0.3440

Max Act: 0.2509. Min Act: -0.0001

Data Index: 904665 (C4 (Web Text))

Max Activating Token Index: 140