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

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

Neuron 86 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: 0.2859. Min Range: -0.2859

Max Act: 0.2859. Min Act: -0.0001

Data Index: 1299920 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2770. Min Act: -0.0001

Data Index: 560547 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2523. Min Act: -0.0001

Data Index: 792157 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2615. Min Act: -0.0001

Data Index: 1252075 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2463. Min Act: -0.0000

Data Index: 500857 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2505. Min Act: -0.0000

Data Index: 506247 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2492. Min Act: -0.0001

Data Index: 1030742 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2211. Min Act: -0.0000

Data Index: 719118 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2329. Min Act: -0.0000

Data Index: 177475 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2492. Min Act: -0.0000

Data Index: 53701 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2029. Min Act: -0.0000

Data Index: 754373 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2231. Min Act: -0.0001

Data Index: 245836 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2200. Min Act: -0.0000

Data Index: 405033 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1059428 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2424. Min Act: -0.0001

Data Index: 615681 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2434. Min Act: -0.0001

Data Index: 456635 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2270. Min Act: -0.0000

Data Index: 269361 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2192. Min Act: -0.0000

Data Index: 1196967 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2125. Min Act: -0.0000

Data Index: 989633 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.2859. Min Range: -0.2859

Max Act: 0.2255. Min Act: -0.0001

Data Index: 959213 (C4 (Web Text))

Max Activating Token Index: 1007