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

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

Neuron 1529 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2648. Min Act: -0.0000

Data Index: 764740 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1001769 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2532. Min Act: -0.0000

Data Index: 339584 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1047439 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1246661 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2361. Min Act: -0.0000

Data Index: 137571 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2306. Min Act: -0.0000

Data Index: 464279 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2376. Min Act: -0.0000

Data Index: 339698 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1123729 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1275191 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1311028 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2157. Min Act: -0.0000

Data Index: 389331 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1133722 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2131. Min Act: -0.0000

Data Index: 289402 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1241928 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1157252 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1971. Min Act: -0.0000

Data Index: 709754 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2026. Min Act: -0.0000

Data Index: 56361 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1305878 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.2648. Min Range: -0.2648

Max Act: 0.1999. Min Act: -0.0000

Data Index: 992436 (C4 (Web Text))

Max Activating Token Index: 905