Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3599 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1183829 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1100166 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7192. Min Act: -0.0000

Data Index: 1309326 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7129. Min Act: -0.0000

Data Index: 370360 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.7024. Min Act: -0.0000

Data Index: 614058 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6759. Min Act: -0.0000

Data Index: 45073 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6421. Min Act: -0.0000

Data Index: 65523 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1438273 (Python Code)

Max Activating Token Index: 880

Text #8

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6703. Min Act: -0.0000

Data Index: 1164596 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6688. Min Act: -0.0000

Data Index: 526818 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6452. Min Act: -0.0000

Data Index: 692761 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6632. Min Act: -0.0000

Data Index: 515785 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6632. Min Act: -0.0000

Data Index: 1370079 (Python Code)

Max Activating Token Index: 977

Text #13

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6583. Min Act: -0.0000

Data Index: 492769 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6353. Min Act: -0.0000

Data Index: 759292 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6618. Min Act: -0.0000

Data Index: 834902 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1099231 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.5994. Min Act: -0.0000

Data Index: 54529 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.6180. Min Act: -0.0000

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 866

Text #19

Max Range: 0.7547. Min Range: -0.7547

Max Act: 0.5675. Min Act: -0.0000

Data Index: 236319 (C4 (Web Text))

Max Activating Token Index: 469