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

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

Neuron 1662 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: 0.9962. Min Range: -0.9962

Max Act: 0.9962. Min Act: -0.0000

Data Index: 794935 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.8784. Min Act: -0.0000

Data Index: 294873 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.8435. Min Act: -0.0000

Data Index: 751680 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7729. Min Act: -0.0000

Data Index: 660191 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.8519. Min Act: -0.0000

Data Index: 998497 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7139. Min Act: -0.0000

Data Index: 697534 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7688. Min Act: -0.0000

Data Index: 156713 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7097. Min Act: -0.0000

Data Index: 503054 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7142. Min Act: -0.0000

Data Index: 241559 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7249. Min Act: -0.0000

Data Index: 33175 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7127. Min Act: -0.0000

Data Index: 609910 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.7139. Min Act: -0.0000

Data Index: 965959 (C4 (Web Text))

Max Activating Token Index: 828

Text #12

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6992. Min Act: -0.0000

Data Index: 1602563 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1320084 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1010492 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6429. Min Act: -0.0000

Data Index: 594191 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6857. Min Act: -0.0000

Data Index: 642651 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6403. Min Act: -0.0000

Data Index: 376119 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1022583 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.9962. Min Range: -0.9962

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1398840 (Python Code)

Max Activating Token Index: 865