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

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

Neuron 725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0425. Min Range: -1.0425

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1292205 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9806. Min Act: -0.0000

Data Index: 380270 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1102991 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9150. Min Act: -0.0000

Data Index: 137784 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9018. Min Act: -0.0000

Data Index: 842791 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.9252. Min Act: -0.0000

Data Index: 160384 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1183247 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8963. Min Act: -0.0000

Data Index: 475054 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1016320 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8226. Min Act: -0.0001

Data Index: 1352026 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.7712. Min Act: -0.0000

Data Index: 521236 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8919. Min Act: -0.0000

Data Index: 460919 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.7475. Min Act: -0.0000

Data Index: 3621 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1349771 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1279334 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8228. Min Act: -0.0000

Data Index: 206799 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1334223 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1175636 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.7781. Min Act: -0.0000

Data Index: 477549 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 1.0425. Min Range: -1.0425

Max Act: 0.7942. Min Act: -0.0000

Data Index: 794828 (C4 (Web Text))

Max Activating Token Index: 111