Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1826 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0005

Data Index: 678444 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0225. Min Act: -0.0006

Data Index: 194112 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1104572 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0222. Min Act: -0.0005

Data Index: 195448 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0222. Min Act: -0.0005

Data Index: 1222390 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0221. Min Act: -0.0006

Data Index: 645039 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0211. Min Act: -0.0005

Data Index: 340230 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0213. Min Act: -0.0005

Data Index: 916472 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0213. Min Act: -0.0005

Data Index: 156903 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0213. Min Act: -0.0006

Data Index: 869438 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0213. Min Act: -0.0005

Data Index: 809576 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0212. Min Act: -0.0005

Data Index: 720032 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0212. Min Act: -0.0006

Data Index: 788120 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0211. Min Act: -0.0005

Data Index: 842700 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0216. Min Act: -0.0006

Data Index: 185069 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0211. Min Act: -0.0005

Data Index: 421003 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0211. Min Act: -0.0006

Data Index: 226766 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0215. Min Act: -0.0006

Data Index: 599409 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0210. Min Act: -0.0005

Data Index: 943392 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0210. Min Act: -0.0005

Data Index: 98914 (C4 (Web Text))

Max Activating Token Index: 632