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

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

Neuron 3542 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0311. Min Act: -0.0003

Data Index: 475891 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0003

Data Index: 277005 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0302. Min Act: -0.0003

Data Index: 304395 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0304. Min Act: -0.0003

Data Index: 754679 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1272194 (C4 (Web Text))

Max Activating Token Index: 949

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0314. Min Act: -0.0003

Data Index: 611993 (C4 (Web Text))

Max Activating Token Index: 580

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0299. Min Act: -0.0003

Data Index: 140577 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0301. Min Act: -0.0003

Data Index: 852400 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0306. Min Act: -0.0003

Data Index: 924322 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0301. Min Act: -0.0003

Data Index: 224269 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1012438 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0292. Min Act: -0.0003

Data Index: 3759 (C4 (Web Text))

Max Activating Token Index: 874

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0300. Min Act: -0.0003

Data Index: 673588 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1112597 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0287. Min Act: -0.0003

Data Index: 157033 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0278. Min Act: -0.0003

Data Index: 681150 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0301. Min Act: -0.0003

Data Index: 648698 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0286. Min Act: -0.0003

Data Index: 720067 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1324482 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1339692 (C4 (Web Text))

Max Activating Token Index: 645