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

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

Neuron 4477 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1855. Min Act: -0.0001

Data Index: 46358 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1716. Min Act: -0.0001

Data Index: 721068 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1392. Min Act: -0.0001

Data Index: 996107 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1536. Min Act: -0.0001

Data Index: 158927 (C4 (Web Text))

Max Activating Token Index: 179

Text #4

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1313. Min Act: -0.0001

Data Index: 712550 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1399. Min Act: -0.0001

Data Index: 850154 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1489. Min Act: -0.0001

Data Index: 1290374 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1310. Min Act: -0.0001

Data Index: 847468 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1357. Min Act: -0.0001

Data Index: 1025510 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1408. Min Act: -0.0001

Data Index: 635078 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1109429 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1307. Min Act: -0.0001

Data Index: 720751 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1323. Min Act: -0.0001

Data Index: 995641 (C4 (Web Text))

Max Activating Token Index: 299

Text #13

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1275. Min Act: -0.0001

Data Index: 376909 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1224092 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1267. Min Act: -0.0001

Data Index: 392377 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1355. Min Act: -0.0001

Data Index: 891054 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1215. Min Act: -0.0001

Data Index: 577675 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1221. Min Act: -0.0001

Data Index: 20221 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1220. Min Act: -0.0001

Data Index: 1101375 (C4 (Web Text))

Max Activating Token Index: 21