Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 464 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1879. Min Act: -0.0001

Data Index: 274837 (C4 (Web Text))

Max Activating Token Index: 592

Text #1

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1718. Min Act: -0.0001

Data Index: 223483 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1282380 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1577. Min Act: -0.0001

Data Index: 511774 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1133826 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1402. Min Act: -0.0001

Data Index: 197350 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1336. Min Act: -0.0001

Data Index: 701814 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1100697 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1418. Min Act: -0.0001

Data Index: 334525 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1320. Min Act: -0.0001

Data Index: 822083 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1180415 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1328. Min Act: -0.0001

Data Index: 690796 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1256. Min Act: -0.0001

Data Index: 224755 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1286. Min Act: -0.0001

Data Index: 324665 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1241. Min Act: -0.0001

Data Index: 125556 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1172351 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1205. Min Act: -0.0001

Data Index: 446303 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1192. Min Act: -0.0001

Data Index: 102781 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1319. Min Act: -0.0001

Data Index: 78258 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 0.1879. Min Range: -0.1879

Max Act: 0.1275. Min Act: -0.0001

Data Index: 96684 (C4 (Web Text))

Max Activating Token Index: 169