Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2901 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.3358. Min Act: -0.0001

Data Index: 1208670 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2944. Min Act: -0.0001

Data Index: 1307454 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2851. Min Act: -0.0001

Data Index: 386498 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2781. Min Act: -0.0001

Data Index: 103116 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2640. Min Act: -0.0001

Data Index: 546263 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2666. Min Act: -0.0001

Data Index: 1252164 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2520. Min Act: -0.0001

Data Index: 1299478 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2540. Min Act: -0.0001

Data Index: 748351 (C4 (Web Text))

Max Activating Token Index: 737

Text #8

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2580. Min Act: -0.0001

Data Index: 808992 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1173526 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2490. Min Act: -0.0001

Data Index: 753872 (C4 (Web Text))

Max Activating Token Index: 390

Text #11

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2492. Min Act: -0.0001

Data Index: 639082 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2581. Min Act: -0.0001

Data Index: 936781 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2455. Min Act: -0.0001

Data Index: 1038680 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2450. Min Act: -0.0001

Data Index: 1209266 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2354. Min Act: -0.0001

Data Index: 49193 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2239. Min Act: -0.0001

Data Index: 870863 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2295. Min Act: -0.0001

Data Index: 38186 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2339. Min Act: -0.0001

Data Index: 596829 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.3358. Min Range: -0.3358

Max Act: 0.2192. Min Act: -0.0001

Data Index: 712681 (C4 (Web Text))

Max Activating Token Index: 35