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

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

Neuron 2276 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: 0.1712. Min Range: -0.1712

Max Act: 0.1712. Min Act: -0.0002

Data Index: 601273 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1564. Min Act: -0.0002

Data Index: 814566 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1544. Min Act: -0.0002

Data Index: 143212 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1446. Min Act: -0.0002

Data Index: 46394 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1485. Min Act: -0.0002

Data Index: 284377 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1425. Min Act: -0.0002

Data Index: 1250012 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1028506 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1216674 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1313. Min Act: -0.0002

Data Index: 488013 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1326. Min Act: -0.0002

Data Index: 66896 (C4 (Web Text))

Max Activating Token Index: 661

Text #10

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1274. Min Act: -0.0002

Data Index: 915083 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1216. Min Act: -0.0002

Data Index: 384206 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1262. Min Act: -0.0002

Data Index: 735910 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1248. Min Act: -0.0002

Data Index: 280546 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1212. Min Act: -0.0002

Data Index: 4480 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1235. Min Act: -0.0002

Data Index: 1347027 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1224432 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1099424 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1312. Min Act: -0.0002

Data Index: 526029 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.1712. Min Range: -0.1712

Max Act: 0.1219. Min Act: -0.0002

Data Index: 485707 (C4 (Web Text))

Max Activating Token Index: 631