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

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

Neuron 662 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1057468 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0365. Min Act: -0.0002

Data Index: 31410 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0354. Min Act: -0.0002

Data Index: 709438 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0304. Min Act: -0.0002

Data Index: 255534 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0301. Min Act: -0.0002

Data Index: 681244 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1312882 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1305336 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0280. Min Act: -0.0002

Data Index: 144419 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0270. Min Act: -0.0002

Data Index: 720264 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0268. Min Act: -0.0002

Data Index: 486780 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1260953 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0275. Min Act: -0.0002

Data Index: 85408 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1042338 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0260. Min Act: -0.0002

Data Index: 626256 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0251. Min Act: -0.0002

Data Index: 857450 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0261. Min Act: -0.0002

Data Index: 406055 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0256. Min Act: -0.0002

Data Index: 792796 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0256. Min Act: -0.0002

Data Index: 479985 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0247. Min Act: -0.0002

Data Index: 784669 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1325648 (C4 (Web Text))

Max Activating Token Index: 193