Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2013 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0337. Min Act: -0.0003

Data Index: 132402 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0340. Min Act: -0.0003

Data Index: 606964 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0003

Data Index: 360308 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0340. Min Act: -0.0003

Data Index: 111012 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0330. Min Act: -0.0004

Data Index: 462274 (C4 (Web Text))

Max Activating Token Index: 927

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0304. Min Act: -0.0003

Data Index: 921493 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1304585 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0318. Min Act: -0.0003

Data Index: 954050 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1310360 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0331. Min Act: -0.0004

Data Index: 598466 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0315. Min Act: -0.0003

Data Index: 818301 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1153994 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0314. Min Act: -0.0003

Data Index: 376601 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0289. Min Act: -0.0003

Data Index: 789615 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0319. Min Act: -0.0003

Data Index: 235478 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1153847 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0288. Min Act: -0.0003

Data Index: 951477 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0296. Min Act: -0.0003

Data Index: 265918 (C4 (Web Text))

Max Activating Token Index: 996

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0265. Min Act: -0.0003

Data Index: 15514 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0269. Min Act: -0.0003

Data Index: 148927 (C4 (Web Text))

Max Activating Token Index: 562