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

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

Neuron 1495 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: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0001

Data Index: 848086 (C4 (Web Text))

Max Activating Token Index: 641

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1014127 (C4 (Web Text))

Max Activating Token Index: 927

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0338. Min Act: -0.0001

Data Index: 195756 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0311. Min Act: -0.0001

Data Index: 785385 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0299. Min Act: -0.0001

Data Index: 157824 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0271. Min Act: -0.0001

Data Index: 321054 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0268. Min Act: -0.0001

Data Index: 22450 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0282. Min Act: -0.0001

Data Index: 158736 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0253. Min Act: -0.0001

Data Index: 220111 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0267. Min Act: -0.0001

Data Index: 370809 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0261. Min Act: -0.0001

Data Index: 1304097 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0253. Min Act: -0.0001

Data Index: 292202 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1188792 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1307365 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0253. Min Act: -0.0001

Data Index: 898779 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0238. Min Act: -0.0001

Data Index: 257806 (C4 (Web Text))

Max Activating Token Index: 169

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0243. Min Act: -0.0001

Data Index: 461220 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0229. Min Act: -0.0001

Data Index: 665448 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1004362 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0238. Min Act: -0.0001

Data Index: 258295 (C4 (Web Text))

Max Activating Token Index: 817