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

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

Neuron 109 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: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0003

Data Index: 25865 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0300. Min Act: -0.0003

Data Index: 639252 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1102843 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0296. Min Act: -0.0003

Data Index: 1609742 (Python Code)

Max Activating Token Index: 422

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0288. Min Act: -0.0004

Data Index: 699724 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0278. Min Act: -0.0003

Data Index: 764885 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1344697 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0275. Min Act: -0.0003

Data Index: 196654 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0278. Min Act: -0.0003

Data Index: 502282 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0265. Min Act: -0.0004

Data Index: 1222744 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1177187 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1116865 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0270. Min Act: -0.0003

Data Index: 872551 (C4 (Web Text))

Max Activating Token Index: 360

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0265. Min Act: -0.0003

Data Index: 637130 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1655628 (Python Code)

Max Activating Token Index: 904

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1536248 (Python Code)

Max Activating Token Index: 665

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0269. Min Act: -0.0004

Data Index: 322829 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0264. Min Act: -0.0003

Data Index: 154135 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0264. Min Act: -0.0003

Data Index: 110708 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1008957 (C4 (Web Text))

Max Activating Token Index: 686