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

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

Neuron 5182 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.7225. Min Act: -0.0001

Data Index: 714 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.5975. Min Act: -0.0000

Data Index: 1103253 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.4600. Min Act: -0.0000

Data Index: 140972 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.3964. Min Act: -0.0000

Data Index: 391006 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.5440. Min Act: -0.0001

Data Index: 1148390 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.3871. Min Act: -0.0001

Data Index: 861793 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.3689. Min Act: -0.0000

Data Index: 842610 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.3444. Min Act: -0.0000

Data Index: 1283020 (C4 (Web Text))

Max Activating Token Index: 829

Text #8

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.3583. Min Act: -0.0001

Data Index: 311394 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.2436. Min Act: -0.0000

Data Index: 879215 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.4660. Min Act: -0.0001

Data Index: 1210823 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.3719. Min Act: -0.0001

Data Index: 464207 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.2023. Min Act: -0.0000

Data Index: 727805 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.1481. Min Act: -0.0001

Data Index: 419101 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.1838. Min Act: -0.0001

Data Index: 545648 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1078014 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.0879. Min Act: -0.0000

Data Index: 526419 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.1633. Min Act: -0.0000

Data Index: 149118 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.1153. Min Act: -0.0000

Data Index: 1256578 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 1.7225. Min Range: -1.7225

Max Act: 1.1516. Min Act: -0.0000

Data Index: 1165100 (C4 (Web Text))

Max Activating Token Index: 536