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

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

Neuron 5450 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1624. Min Act: -0.0000

Data Index: 640667 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1337. Min Act: -0.0001

Data Index: 658398 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1499. Min Act: -0.0000

Data Index: 761527 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1635. Min Act: -0.0000

Data Index: 187806 (C4 (Web Text))

Max Activating Token Index: 707

Text #4

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1406. Min Act: -0.0001

Data Index: 409782 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1448. Min Act: -0.0000

Data Index: 834398 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1342. Min Act: -0.0001

Data Index: 217604 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1394. Min Act: -0.0001

Data Index: 420417 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1283. Min Act: -0.0000

Data Index: 401400 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1327. Min Act: -0.0000

Data Index: 439685 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1378. Min Act: -0.0000

Data Index: 521535 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1375. Min Act: -0.0000

Data Index: 522938 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1403. Min Act: -0.0000

Data Index: 702449 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1341. Min Act: -0.0000

Data Index: 1194488 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1293. Min Act: -0.0000

Data Index: 870859 (C4 (Web Text))

Max Activating Token Index: 53

Text #15

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1216. Min Act: -0.0000

Data Index: 82302 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1221. Min Act: -0.0000

Data Index: 403056 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1177. Min Act: -0.0000

Data Index: 536046 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1155. Min Act: -0.0000

Data Index: 239071 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.1635. Min Range: -0.1635

Max Act: 0.1207. Min Act: -0.0000

Data Index: 1032790 (C4 (Web Text))

Max Activating Token Index: 621