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

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

Neuron 5073 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: 1.7399. Min Range: -1.7399

Max Act: 1.7399. Min Act: -0.0000

Data Index: 344863 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.6966. Min Act: -0.0000

Data Index: 695956 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.6079. Min Act: -0.0000

Data Index: 744412 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.6974. Min Act: -0.0000

Data Index: 553839 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1268944 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1277574 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4669. Min Act: -0.0000

Data Index: 762857 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4432. Min Act: -0.0000

Data Index: 286629 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3396. Min Act: -0.0000

Data Index: 1287373 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3567. Min Act: -0.0000

Data Index: 1153650 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2740. Min Act: -0.0000

Data Index: 35326 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3651. Min Act: -0.0000

Data Index: 921031 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3742. Min Act: -0.0000

Data Index: 1262235 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.3250. Min Act: -0.0000

Data Index: 603485 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2826. Min Act: -0.0000

Data Index: 618505 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1504. Min Act: -0.0000

Data Index: 670722 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2448. Min Act: -0.0000

Data Index: 1072993 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1737. Min Act: -0.0000

Data Index: 1081271 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2357. Min Act: -0.0000

Data Index: 1291329 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.2388. Min Act: -0.0000

Data Index: 551224 (C4 (Web Text))

Max Activating Token Index: 1019