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

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

Neuron 3528 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1430. Min Act: -0.0000

Data Index: 175164 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1310. Min Act: -0.0000

Data Index: 434525 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1031999 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1247. Min Act: -0.0000

Data Index: 180576 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1305. Min Act: -0.0000

Data Index: 640716 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1295. Min Act: -0.0000

Data Index: 582172 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1287. Min Act: -0.0000

Data Index: 264892 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1265. Min Act: -0.0000

Data Index: 873329 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1250. Min Act: -0.0000

Data Index: 38433 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1202. Min Act: -0.0000

Data Index: 150520 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1234. Min Act: -0.0000

Data Index: 829812 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1230. Min Act: -0.0000

Data Index: 275854 (C4 (Web Text))

Max Activating Token Index: 235

Text #12

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1259599 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1206. Min Act: -0.0000

Data Index: 451541 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1352937 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1192. Min Act: -0.0000

Data Index: 941316 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1205. Min Act: -0.0000

Data Index: 377485 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1251. Min Act: -0.0000

Data Index: 186626 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1166. Min Act: -0.0000

Data Index: 145952 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.1430. Min Range: -0.1430

Max Act: 0.1190. Min Act: -0.0000

Data Index: 229948 (C4 (Web Text))

Max Activating Token Index: 879