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

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

Neuron 1968 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1599. Min Act: -0.0001

Data Index: 901356 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1620. Min Act: -0.0001

Data Index: 828279 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1408. Min Act: -0.0001

Data Index: 992484 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1450. Min Act: -0.0001

Data Index: 947384 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1384. Min Act: -0.0001

Data Index: 548354 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1280. Min Act: -0.0001

Data Index: 816832 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1331. Min Act: -0.0001

Data Index: 1062220 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1205. Min Act: -0.0001

Data Index: 124335 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1176. Min Act: -0.0001

Data Index: 1079509 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1272. Min Act: -0.0001

Data Index: 885922 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1265. Min Act: -0.0001

Data Index: 401857 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1312. Min Act: -0.0001

Data Index: 347556 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1304. Min Act: -0.0001

Data Index: 973901 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1218. Min Act: -0.0001

Data Index: 608245 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1257. Min Act: -0.0001

Data Index: 381812 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1076216 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1233. Min Act: -0.0001

Data Index: 631633 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1057. Min Act: -0.0001

Data Index: 1279915 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1213. Min Act: -0.0001

Data Index: 1138754 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.1620. Min Range: -0.1620

Max Act: 0.1242. Min Act: -0.0001

Data Index: 1306181 (C4 (Web Text))

Max Activating Token Index: 636