Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3551 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.6400. Min Act: -0.0000

Data Index: 630249 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.6192. Min Act: -0.0000

Data Index: 333061 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5687. Min Act: -0.0000

Data Index: 219581 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5308. Min Act: -0.0000

Data Index: 441186 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.5164. Min Act: -0.0000

Data Index: 436028 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1186807 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4558. Min Act: -0.0000

Data Index: 104569 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4520. Min Act: -0.0000

Data Index: 476255 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4311. Min Act: -0.0000

Data Index: 926932 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4578. Min Act: -0.0000

Data Index: 900059 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1058956 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4214. Min Act: -0.0000

Data Index: 13848 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4532. Min Act: -0.0000

Data Index: 847872 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4251. Min Act: -0.0000

Data Index: 248798 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4382. Min Act: -0.0000

Data Index: 799791 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1349607 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4384. Min Act: -0.0000

Data Index: 63856 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.4048. Min Act: -0.0000

Data Index: 668533 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.3593. Min Act: -0.0000

Data Index: 354552 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.6400. Min Range: -0.6400

Max Act: 0.3886. Min Act: -0.0000

Data Index: 957271 (C4 (Web Text))

Max Activating Token Index: 842