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

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

Neuron 633 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0331. Min Act: -0.0002

Data Index: 911475 (C4 (Web Text))

Max Activating Token Index: 5

Text #1

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1097773 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0275. Min Act: -0.0002

Data Index: 528237 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0267. Min Act: -0.0002

Data Index: 685216 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0259. Min Act: -0.0002

Data Index: 373115 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0263. Min Act: -0.0002

Data Index: 606063 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0271. Min Act: -0.0002

Data Index: 101629 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0276. Min Act: -0.0002

Data Index: 944613 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1100474 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0264. Min Act: -0.0002

Data Index: 947418 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0258. Min Act: -0.0002

Data Index: 639340 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1221259 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0257. Min Act: -0.0002

Data Index: 755118 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1147618 (C4 (Web Text))

Max Activating Token Index: 28

Text #14

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0249. Min Act: -0.0002

Data Index: 1179151 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0240. Min Act: -0.0002

Data Index: 1488242 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0226. Min Act: -0.0002

Data Index: 523224 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0240. Min Act: -0.0002

Data Index: 606569 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0233. Min Act: -0.0002

Data Index: 1280061 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.0331. Min Range: -0.0331

Max Act: 0.0237. Min Act: -0.0002

Data Index: 776397 (C4 (Web Text))

Max Activating Token Index: 947