Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 498 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1236554 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1561. Min Act: -0.0001

Data Index: 767176 (C4 (Web Text))

Max Activating Token Index: 672

Text #2

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1446. Min Act: -0.0001

Data Index: 930406 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1404. Min Act: -0.0001

Data Index: 196020 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1136708 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1339. Min Act: -0.0001

Data Index: 469029 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1342280 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1063891 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1295. Min Act: -0.0001

Data Index: 913271 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1329. Min Act: -0.0001

Data Index: 986138 (C4 (Web Text))

Max Activating Token Index: 222

Text #10

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1273. Min Act: -0.0001

Data Index: 1290798 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1337. Min Act: -0.0001

Data Index: 538033 (C4 (Web Text))

Max Activating Token Index: 545

Text #12

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1349. Min Act: -0.0001

Data Index: 372928 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1300. Min Act: -0.0001

Data Index: 761019 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1280. Min Act: -0.0001

Data Index: 1078911 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1258. Min Act: -0.0001

Data Index: 842530 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1189052 (C4 (Web Text))

Max Activating Token Index: 325

Text #17

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1314. Min Act: -0.0001

Data Index: 894965 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1186028 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.1616. Min Range: -0.1616

Max Act: 0.1306. Min Act: -0.0001

Data Index: 921246 (C4 (Web Text))

Max Activating Token Index: 381