Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3595 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1297004 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.4542. Min Act: -0.0000

Data Index: 894551 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.3241. Min Act: -0.0000

Data Index: 320671 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2938. Min Act: -0.0000

Data Index: 132619 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2787. Min Act: 0.0000

Data Index: 725275 (C4 (Web Text))

Max Activating Token Index: 468

Text #5

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2809. Min Act: -0.0000

Data Index: 70910 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2702. Min Act: -0.0000

Data Index: 491617 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2602. Min Act: -0.0000

Data Index: 793106 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2390. Min Act: 0.0000

Data Index: 1148403 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2368. Min Act: -0.0000

Data Index: 853521 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2299. Min Act: -0.0000

Data Index: 570512 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2233. Min Act: -0.0000

Data Index: 324127 (C4 (Web Text))

Max Activating Token Index: 758

Text #12

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2448. Min Act: -0.0000

Data Index: 1005791 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2268. Min Act: -0.0000

Data Index: 106514 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2212. Min Act: -0.0000

Data Index: 296593 (C4 (Web Text))

Max Activating Token Index: 771

Text #15

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2195. Min Act: -0.0000

Data Index: 903757 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2203. Min Act: -0.0000

Data Index: 1229710 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1261273 (C4 (Web Text))

Max Activating Token Index: 991

Text #18

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2196. Min Act: -0.0000

Data Index: 264816 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.6285. Min Range: -0.6285

Max Act: 0.2110. Min Act: -0.0000

Data Index: 93722 (C4 (Web Text))

Max Activating Token Index: 521