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

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

Neuron 4647 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: 0.1450. Min Range: -0.1450

Max Act: 0.1450. Min Act: -0.0002

Data Index: 1310944 (C4 (Web Text))

Max Activating Token Index: 367

Text #1

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1448. Min Act: -0.0002

Data Index: 143111 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1430. Min Act: -0.0002

Data Index: 581655 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1341. Min Act: -0.0002

Data Index: 58556 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1383. Min Act: -0.0002

Data Index: 452512 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1317. Min Act: -0.0002

Data Index: 662292 (C4 (Web Text))

Max Activating Token Index: 384

Text #6

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1332. Min Act: -0.0002

Data Index: 903274 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1328. Min Act: -0.0002

Data Index: 933085 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1368. Min Act: -0.0002

Data Index: 861076 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1259. Min Act: -0.0002

Data Index: 959159 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1240. Min Act: -0.0002

Data Index: 396527 (C4 (Web Text))

Max Activating Token Index: 245

Text #11

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1058. Min Act: -0.0003

Data Index: 144540 (C4 (Web Text))

Max Activating Token Index: 247

Text #12

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1140. Min Act: -0.0002

Data Index: 85445 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1207. Min Act: -0.0002

Data Index: 845916 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1129. Min Act: -0.0002

Data Index: 752496 (C4 (Web Text))

Max Activating Token Index: 999

Text #15

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1029. Min Act: -0.0002

Data Index: 571318 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1072. Min Act: -0.0002

Data Index: 2614 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1078. Min Act: -0.0002

Data Index: 210565 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1157. Min Act: -0.0002

Data Index: 928115 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 0.1450. Min Range: -0.1450

Max Act: 0.1048. Min Act: -0.0002

Data Index: 859010 (C4 (Web Text))

Max Activating Token Index: 1015