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

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

Neuron 1916 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0001

Data Index: 584881 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0347. Min Act: -0.0001

Data Index: 1244076 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1331837 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1109950 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0328. Min Act: -0.0001

Data Index: 824427 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0333. Min Act: -0.0001

Data Index: 143248 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0319. Min Act: -0.0001

Data Index: 43442 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1189960 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0315. Min Act: -0.0001

Data Index: 1033748 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1267631 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1327608 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0317. Min Act: -0.0001

Data Index: 563945 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1178721 (C4 (Web Text))

Max Activating Token Index: 19

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0296. Min Act: -0.0001

Data Index: 96752 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0302. Min Act: -0.0001

Data Index: 78898 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1144784 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1110294 (C4 (Web Text))

Max Activating Token Index: 255

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0289. Min Act: -0.0001

Data Index: 327270 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0290. Min Act: -0.0001

Data Index: 743412 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0285. Min Act: -0.0001

Data Index: 616962 (C4 (Web Text))

Max Activating Token Index: 120