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

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

Neuron 2143 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: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0001

Data Index: 496677 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1304. Min Act: -0.0001

Data Index: 421599 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1304429 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1307. Min Act: -0.0001

Data Index: 384249 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1235120 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1232. Min Act: -0.0001

Data Index: 302310 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1242. Min Act: -0.0001

Data Index: 300534 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1186. Min Act: -0.0001

Data Index: 713739 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1262. Min Act: -0.0001

Data Index: 1156978 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1163. Min Act: -0.0001

Data Index: 641732 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1180. Min Act: -0.0001

Data Index: 1339454 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1124. Min Act: -0.0001

Data Index: 506718 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0955. Min Act: -0.0001

Data Index: 533674 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1083. Min Act: -0.0001

Data Index: 412662 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1200. Min Act: -0.0001

Data Index: 821139 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1138. Min Act: -0.0001

Data Index: 967536 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1066. Min Act: -0.0001

Data Index: 947312 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1131. Min Act: -0.0001

Data Index: 506927 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1069. Min Act: -0.0001

Data Index: 987178 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1065. Min Act: -0.0001

Data Index: 223347 (C4 (Web Text))

Max Activating Token Index: 581