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

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

Neuron 1 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: 0.0370. Min Range: -0.0370

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1103287 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1179424 (C4 (Web Text))

Max Activating Token Index: 29

Text #2

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1189692 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0338. Min Act: -0.0003

Data Index: 326447 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1211628 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0328. Min Act: -0.0002

Data Index: 858245 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0314. Min Act: -0.0001

Data Index: 862793 (C4 (Web Text))

Max Activating Token Index: 685

Text #7

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0301. Min Act: -0.0003

Data Index: 807795 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1121522 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1029752 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1183752 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0294. Min Act: -0.0003

Data Index: 171079 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1081063 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0285. Min Act: -0.0002

Data Index: 862697 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0282. Min Act: -0.0000

Data Index: 50597 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0282. Min Act: -0.0003

Data Index: 198865 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0284. Min Act: -0.0003

Data Index: 376023 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0293. Min Act: -0.0003

Data Index: 851938 (C4 (Web Text))

Max Activating Token Index: 160

Text #18

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0275. Min Act: -0.0003

Data Index: 827090 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.0370. Min Range: -0.0370

Max Act: 0.0277. Min Act: -0.0003

Data Index: 516380 (C4 (Web Text))

Max Activating Token Index: 550