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

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

Neuron 4128 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1401. Min Act: -0.0001

Data Index: 19174 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1221. Min Act: -0.0001

Data Index: 1036174 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1225. Min Act: -0.0001

Data Index: 235307 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1228. Min Act: -0.0001

Data Index: 712022 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1288. Min Act: -0.0001

Data Index: 1347005 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1237. Min Act: -0.0001

Data Index: 680325 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1272. Min Act: -0.0001

Data Index: 535090 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1249. Min Act: -0.0001

Data Index: 1165068 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1202. Min Act: -0.0001

Data Index: 53836 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1223. Min Act: -0.0001

Data Index: 473054 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1273657 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1283. Min Act: -0.0001

Data Index: 512259 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1149. Min Act: -0.0001

Data Index: 121649 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.0948. Min Act: -0.0001

Data Index: 838440 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1182. Min Act: -0.0001

Data Index: 502231 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1111. Min Act: -0.0001

Data Index: 838236 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1056. Min Act: -0.0001

Data Index: 20816 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1124. Min Act: -0.0001

Data Index: 1317149 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1028. Min Act: -0.0001

Data Index: 705966 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 0.1401. Min Range: -0.1401

Max Act: 0.1194. Min Act: -0.0001

Data Index: 574741 (C4 (Web Text))

Max Activating Token Index: 251