Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3456 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0326. Min Act: -0.0001

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0318. Min Act: -0.0001

Data Index: 1134643 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0317. Min Act: -0.0001

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 338

Text #3

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1139128 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0285. Min Act: 0.0000

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0283. Min Act: -0.0002

Data Index: 725085 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0277. Min Act: -0.0001

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0276. Min Act: -0.0001

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0273. Min Act: -0.0001

Data Index: 280806 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0268. Min Act: -0.0001

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0262. Min Act: -0.0001

Data Index: 593230 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1447943 (Python Code)

Max Activating Token Index: 876

Text #13

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0241. Min Act: -0.0001

Data Index: 1572651 (Python Code)

Max Activating Token Index: 866

Text #14

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0233. Min Act: -0.0001

Data Index: 1620680 (Python Code)

Max Activating Token Index: 875

Text #15

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0232. Min Act: -0.0001

Data Index: 1594469 (Python Code)

Max Activating Token Index: 876

Text #16

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0224. Min Act: -0.0001

Data Index: 1591700 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1638072 (Python Code)

Max Activating Token Index: 760

Text #18

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1432514 (Python Code)

Max Activating Token Index: 934

Text #19

Max Range: 0.0326. Min Range: -0.0326

Max Act: 0.0227. Min Act: -0.0001

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 258