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

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

Neuron 942 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: 0.4934. Min Range: -0.4934

Max Act: 0.4934. Min Act: -0.0001

Data Index: 292674 (C4 (Web Text))

Max Activating Token Index: 406

Text #1

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.4520. Min Act: -0.0001

Data Index: 70315 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3881. Min Act: -0.0001

Data Index: 1285217 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3600. Min Act: -0.0001

Data Index: 714593 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3453. Min Act: -0.0001

Data Index: 54804 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3807. Min Act: -0.0001

Data Index: 236726 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3645. Min Act: -0.0001

Data Index: 61151 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3785. Min Act: -0.0001

Data Index: 853722 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3326. Min Act: -0.0001

Data Index: 975331 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3350. Min Act: -0.0001

Data Index: 577013 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3522. Min Act: -0.0001

Data Index: 742481 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3462. Min Act: -0.0001

Data Index: 556130 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3520. Min Act: -0.0001

Data Index: 1300754 (C4 (Web Text))

Max Activating Token Index: 705

Text #13

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3303. Min Act: -0.0001

Data Index: 64332 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3340. Min Act: -0.0001

Data Index: 583248 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3371. Min Act: -0.0001

Data Index: 29052 (C4 (Web Text))

Max Activating Token Index: 289

Text #16

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1580833 (Python Code)

Max Activating Token Index: 702

Text #17

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3280. Min Act: -0.0001

Data Index: 1174078 (C4 (Web Text))

Max Activating Token Index: 341

Text #18

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3177. Min Act: -0.0001

Data Index: 845303 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.4934. Min Range: -0.4934

Max Act: 0.3222. Min Act: -0.0001

Data Index: 522255 (C4 (Web Text))

Max Activating Token Index: 569