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

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

Neuron 142 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1420. Min Act: -0.0002

Data Index: 1134524 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1427. Min Act: -0.0002

Data Index: 779323 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1364. Min Act: -0.0002

Data Index: 637083 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1337. Min Act: -0.0002

Data Index: 689124 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1262. Min Act: -0.0002

Data Index: 553704 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1270. Min Act: -0.0002

Data Index: 451128 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1270. Min Act: -0.0002

Data Index: 322493 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1197. Min Act: -0.0002

Data Index: 946983 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1173. Min Act: -0.0002

Data Index: 1226219 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1230. Min Act: -0.0003

Data Index: 741283 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1156. Min Act: -0.0002

Data Index: 604576 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1214. Min Act: -0.0002

Data Index: 10409 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1260. Min Act: -0.0002

Data Index: 1018158 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1104. Min Act: -0.0003

Data Index: 90120 (C4 (Web Text))

Max Activating Token Index: 347

Text #14

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1251. Min Act: -0.0002

Data Index: 1140015 (C4 (Web Text))

Max Activating Token Index: 852

Text #15

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1205201 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1373999 (Python Code)

Max Activating Token Index: 647

Text #17

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1131. Min Act: -0.0002

Data Index: 222280 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1112. Min Act: -0.0002

Data Index: 1019263 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.1427. Min Range: -0.1427

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1122470 (C4 (Web Text))

Max Activating Token Index: 732