Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3439 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0365. Min Act: -0.0001

Data Index: 541063 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0324. Min Act: -0.0001

Data Index: 349827 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1065943 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1158383 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0291. Min Act: -0.0001

Data Index: 3069 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0282. Min Act: -0.0001

Data Index: 998558 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0282. Min Act: -0.0001

Data Index: 951009 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0282. Min Act: -0.0001

Data Index: 674556 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1150703 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0278. Min Act: -0.0001

Data Index: 265271 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0276. Min Act: -0.0001

Data Index: 1319872 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0271. Min Act: -0.0001

Data Index: 493536 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0255. Min Act: -0.0001

Data Index: 993782 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0239. Min Act: -0.0001

Data Index: 305387 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0262. Min Act: -0.0001

Data Index: 27915 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0248. Min Act: -0.0001

Data Index: 319579 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1197747 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0249. Min Act: -0.0001

Data Index: 282054 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0251. Min Act: -0.0001

Data Index: 23181 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0365. Min Range: -0.0365

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1147250 (C4 (Web Text))

Max Activating Token Index: 499