Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2018 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0246. Min Act: -0.0004

Data Index: 1412769 (Python Code)

Max Activating Token Index: 693

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0004

Data Index: 1507079 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1403241 (Python Code)

Max Activating Token Index: 89

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1450882 (Python Code)

Max Activating Token Index: 768

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1457914 (Python Code)

Max Activating Token Index: 443

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0242. Min Act: -0.0004

Data Index: 1392318 (Python Code)

Max Activating Token Index: 342

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1616886 (Python Code)

Max Activating Token Index: 928

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0241. Min Act: -0.0004

Data Index: 1559065 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1368104 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0238. Min Act: -0.0004

Data Index: 1455392 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1559350 (Python Code)

Max Activating Token Index: 744

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1549470 (Python Code)

Max Activating Token Index: 246

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1526870 (Python Code)

Max Activating Token Index: 131

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1657093 (Python Code)

Max Activating Token Index: 825

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0231. Min Act: -0.0004

Data Index: 1438667 (Python Code)

Max Activating Token Index: 820

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1480367 (Python Code)

Max Activating Token Index: 685

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1584396 (Python Code)

Max Activating Token Index: 268

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0222. Min Act: -0.0004

Data Index: 1387782 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0222. Min Act: -0.0004

Data Index: 1540492 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1454264 (Python Code)

Max Activating Token Index: 766