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

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

Neuron 3231 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.6609. Min Act: -0.0001

Data Index: 1260529 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5500. Min Act: -0.0001

Data Index: 850671 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.6098. Min Act: -0.0001

Data Index: 712711 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.6018. Min Act: -0.0001

Data Index: 1323292 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5845. Min Act: -0.0001

Data Index: 796948 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.6125. Min Act: -0.0001

Data Index: 1222617 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5204. Min Act: -0.0001

Data Index: 1577850 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5696. Min Act: -0.0001

Data Index: 145692 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5351. Min Act: -0.0001

Data Index: 652222 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5180. Min Act: -0.0001

Data Index: 823021 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5600. Min Act: -0.0001

Data Index: 809020 (C4 (Web Text))

Max Activating Token Index: 526

Text #11

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5274. Min Act: -0.0001

Data Index: 1014643 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.4934. Min Act: -0.0001

Data Index: 261431 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5706. Min Act: -0.0001

Data Index: 1578200 (Python Code)

Max Activating Token Index: 853

Text #14

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.4917. Min Act: -0.0001

Data Index: 263996 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5191. Min Act: -0.0001

Data Index: 501989 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.5141. Min Act: -0.0001

Data Index: 1149181 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.4984. Min Act: -0.0001

Data Index: 1045154 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.4966. Min Act: -0.0001

Data Index: 621968 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.6609. Min Range: -0.6609

Max Act: 0.4942. Min Act: -0.0001

Data Index: 1512454 (Python Code)

Max Activating Token Index: 516