Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1647 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1612016 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1585621 (Python Code)

Max Activating Token Index: 486

Text #2

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0244. Min Act: -0.0003

Data Index: 637513 (C4 (Web Text))

Max Activating Token Index: 581

Text #3

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1624049 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0243. Min Act: -0.0003

Data Index: 1384759 (Python Code)

Max Activating Token Index: 345

Text #5

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0247. Min Act: -0.0003

Data Index: 1521278 (Python Code)

Max Activating Token Index: 778

Text #6

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1547685 (Python Code)

Max Activating Token Index: 774

Text #7

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0243. Min Act: -0.0003

Data Index: 901746 (C4 (Web Text))

Max Activating Token Index: 999

Text #8

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1646513 (Python Code)

Max Activating Token Index: 1016

Text #9

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1009182 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0233. Min Act: -0.0003

Data Index: 586474 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1593158 (Python Code)

Max Activating Token Index: 965

Text #12

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0235. Min Act: -0.0004

Data Index: 611972 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0003

Data Index: 625976 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0225. Min Act: -0.0003

Data Index: 1532227 (Python Code)

Max Activating Token Index: 424

Text #15

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1633678 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0225. Min Act: -0.0003

Data Index: 970602 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1552089 (Python Code)

Max Activating Token Index: 941

Text #18

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0004

Data Index: 602830 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.0266. Min Range: -0.0266

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1083478 (C4 (Web Text))

Max Activating Token Index: 18