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

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

Neuron 467 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1392591 (Python Code)

Max Activating Token Index: 862

Text #1

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.7661. Min Act: -0.0000

Data Index: 1586768 (Python Code)

Max Activating Token Index: 516

Text #2

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1640354 (Python Code)

Max Activating Token Index: 498

Text #3

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1626437 (Python Code)

Max Activating Token Index: 588

Text #4

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6159. Min Act: -0.0000

Data Index: 1554420 (Python Code)

Max Activating Token Index: 880

Text #5

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1528560 (Python Code)

Max Activating Token Index: 867

Text #6

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5899. Min Act: -0.0000

Data Index: 1445345 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1430453 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5786. Min Act: -0.0000

Data Index: 1552245 (Python Code)

Max Activating Token Index: 935

Text #9

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1446075 (Python Code)

Max Activating Token Index: 999

Text #10

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1483320 (Python Code)

Max Activating Token Index: 987

Text #11

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1413931 (Python Code)

Max Activating Token Index: 39

Text #12

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5982. Min Act: -0.0000

Data Index: 1601425 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1579092 (Python Code)

Max Activating Token Index: 410

Text #14

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5400. Min Act: -0.0000

Data Index: 1579420 (Python Code)

Max Activating Token Index: 92

Text #15

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5523. Min Act: -0.0000

Data Index: 1425362 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1367217 (Python Code)

Max Activating Token Index: 118

Text #17

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1567858 (Python Code)

Max Activating Token Index: 995

Text #18

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5845. Min Act: -0.0000

Data Index: 1364632 (Python Code)

Max Activating Token Index: 252

Text #19

Max Range: 0.8176. Min Range: -0.8176

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1630957 (Python Code)

Max Activating Token Index: 661