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

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

Neuron 2376 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: 0.1965. Min Range: -0.1965

Max Act: 0.1965. Min Act: -0.0002

Data Index: 409041 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1669. Min Act: -0.0002

Data Index: 606539 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1547. Min Act: -0.0002

Data Index: 1159372 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1593. Min Act: -0.0002

Data Index: 1341257 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1474. Min Act: -0.0002

Data Index: 155379 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1391. Min Act: -0.0002

Data Index: 356236 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1469. Min Act: -0.0002

Data Index: 471447 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1433. Min Act: -0.0002

Data Index: 790616 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1266. Min Act: -0.0002

Data Index: 1349552 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1271. Min Act: -0.0002

Data Index: 564320 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1412. Min Act: -0.0002

Data Index: 761661 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1175. Min Act: -0.0002

Data Index: 367144 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1354. Min Act: -0.0002

Data Index: 555907 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1205. Min Act: -0.0002

Data Index: 419401 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1234. Min Act: -0.0002

Data Index: 180585 (C4 (Web Text))

Max Activating Token Index: 208

Text #15

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1137144 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1183. Min Act: -0.0002

Data Index: 724612 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1254. Min Act: -0.0002

Data Index: 218364 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1264. Min Act: -0.0002

Data Index: 897642 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1015839 (C4 (Web Text))

Max Activating Token Index: 213