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

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

Neuron 4631 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.4225. Min Act: -0.0000

Data Index: 781738 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.2360. Min Act: -0.0000

Data Index: 530516 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.3475. Min Act: -0.0000

Data Index: 1161215 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.2772. Min Act: -0.0000

Data Index: 1173644 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.2981. Min Act: -0.0000

Data Index: 818960 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.1615. Min Act: -0.0000

Data Index: 782064 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.2163. Min Act: -0.0000

Data Index: 172038 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.3722. Min Act: -0.0000

Data Index: 1197987 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 2.4225. Min Range: -2.4225

Max Act: 1.9934. Min Act: -0.0000

Data Index: 1042519 (C4 (Web Text))

Max Activating Token Index: 906

Text #9

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.0441. Min Act: -0.0000

Data Index: 543243 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.2376. Min Act: -0.0000

Data Index: 1149198 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.0240. Min Act: -0.0000

Data Index: 1254058 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.0727. Min Act: -0.0000

Data Index: 852630 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 2.4225. Min Range: -2.4225

Max Act: 2.1551. Min Act: -0.0000

Data Index: 564331 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 2.4225. Min Range: -2.4225

Max Act: 1.9958. Min Act: -0.0000

Data Index: 990361 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 2.4225. Min Range: -2.4225

Max Act: 1.8674. Min Act: -0.0000

Data Index: 1193623 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 2.4225. Min Range: -2.4225

Max Act: 1.8884. Min Act: -0.0000

Data Index: 160256 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 2.4225. Min Range: -2.4225

Max Act: 1.9085. Min Act: -0.0000

Data Index: 669951 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 2.4225. Min Range: -2.4225

Max Act: 1.7727. Min Act: -0.0000

Data Index: 370884 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 2.4225. Min Range: -2.4225

Max Act: 1.8623. Min Act: -0.0000

Data Index: 829144 (C4 (Web Text))

Max Activating Token Index: 495