Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5661 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0002

Data Index: 774655 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0345. Min Act: -0.0002

Data Index: 709546 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0312. Min Act: -0.0002

Data Index: 114401 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0300. Min Act: -0.0002

Data Index: 931559 (C4 (Web Text))

Max Activating Token Index: 369

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0276. Min Act: -0.0002

Data Index: 155514 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0276. Min Act: -0.0002

Data Index: 165026 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0002

Data Index: 346374 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0257. Min Act: -0.0002

Data Index: 217342 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0260. Min Act: -0.0002

Data Index: 515843 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0254. Min Act: -0.0002

Data Index: 755923 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0253. Min Act: -0.0002

Data Index: 547107 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0257. Min Act: -0.0002

Data Index: 713881 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0243. Min Act: -0.0002

Data Index: 169394 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0248. Min Act: -0.0002

Data Index: 634090 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1091323 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0252. Min Act: -0.0002

Data Index: 1334245 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0222. Min Act: -0.0002

Data Index: 882045 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0230. Min Act: -0.0002

Data Index: 956733 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0230. Min Act: -0.0002

Data Index: 900993 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1202165 (C4 (Web Text))

Max Activating Token Index: 285