Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1195 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.4682. Min Range: -5.4682

Max Act: 5.4682. Min Act: -0.0001

Data Index: 308671 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 5.4682. Min Range: -5.4682

Max Act: 5.2616. Min Act: -0.0001

Data Index: 593683 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 5.4682. Min Range: -5.4682

Max Act: 4.3546. Min Act: -0.0001

Data Index: 196584 (C4 (Web Text))

Max Activating Token Index: 897

Text #3

Max Range: 5.4682. Min Range: -5.4682

Max Act: 4.2416. Min Act: -0.0001

Data Index: 411578 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.7378. Min Act: -0.0000

Data Index: 1006296 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 5.4682. Min Range: -5.4682

Max Act: 4.0441. Min Act: -0.0001

Data Index: 60088 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 5.4682. Min Range: -5.4682

Max Act: 4.1641. Min Act: -0.0001

Data Index: 157406 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.9355. Min Act: -0.0001

Data Index: 206857 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.9028. Min Act: -0.0001

Data Index: 878636 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.7374. Min Act: -0.0001

Data Index: 232536 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.8503. Min Act: -0.0001

Data Index: 86382 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.7028. Min Act: -0.0001

Data Index: 1309665 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.6731. Min Act: -0.0001

Data Index: 348882 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.4915. Min Act: -0.0001

Data Index: 1008600 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.8672. Min Act: -0.0001

Data Index: 393412 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.6992. Min Act: -0.0001

Data Index: 1238742 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.6977. Min Act: -0.0001

Data Index: 320919 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.8405. Min Act: -0.0001

Data Index: 867154 (C4 (Web Text))

Max Activating Token Index: 331

Text #18

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.6368. Min Act: -0.0001

Data Index: 62216 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 5.4682. Min Range: -5.4682

Max Act: 3.5987. Min Act: -0.0001

Data Index: 961230 (C4 (Web Text))

Max Activating Token Index: 653