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

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

Neuron 4958 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: 0.1787. Min Range: -0.1787

Max Act: 0.1787. Min Act: -0.0001

Data Index: 61237 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1379. Min Act: -0.0001

Data Index: 405621 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1337. Min Act: -0.0001

Data Index: 116111 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1382. Min Act: -0.0001

Data Index: 513546 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1293. Min Act: -0.0001

Data Index: 103808 (C4 (Web Text))

Max Activating Token Index: 458

Text #5

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1265654 (C4 (Web Text))

Max Activating Token Index: 86

Text #6

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1015743 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1126258 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1209. Min Act: -0.0001

Data Index: 389507 (C4 (Web Text))

Max Activating Token Index: 765

Text #9

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1279. Min Act: -0.0001

Data Index: 179750 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1146. Min Act: -0.0001

Data Index: 21561 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1221115 (C4 (Web Text))

Max Activating Token Index: 337

Text #12

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1088. Min Act: -0.0001

Data Index: 82877 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1211874 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1164. Min Act: -0.0001

Data Index: 891102 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1060. Min Act: -0.0001

Data Index: 58715 (C4 (Web Text))

Max Activating Token Index: 343

Text #16

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1182. Min Act: -0.0001

Data Index: 646469 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1123. Min Act: -0.0001

Data Index: 662587 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1143. Min Act: -0.0001

Data Index: 514544 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1787. Min Range: -0.1787

Max Act: 0.1185. Min Act: -0.0001

Data Index: 116267 (C4 (Web Text))

Max Activating Token Index: 698