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

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

Neuron 26 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: 2.8615. Min Range: -2.8615

Max Act: 2.8615. Min Act: -0.0000

Data Index: 897903 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.5691. Min Act: -0.0000

Data Index: 1156572 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.5626. Min Act: -0.0000

Data Index: 1214215 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.2336. Min Act: -0.0000

Data Index: 803221 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0204. Min Act: -0.0000

Data Index: 1039296 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0696. Min Act: -0.0000

Data Index: 161629 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1794. Min Act: -0.0000

Data Index: 431543 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0451. Min Act: -0.0000

Data Index: 341683 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.2649. Min Act: -0.0000

Data Index: 400785 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0335. Min Act: -0.0000

Data Index: 664817 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1069. Min Act: -0.0000

Data Index: 967954 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.9557. Min Act: -0.0000

Data Index: 1240529 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.1720. Min Act: -0.0000

Data Index: 1351048 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 2.8615. Min Range: -2.8615

Max Act: 2.0774. Min Act: -0.0000

Data Index: 354748 (C4 (Web Text))

Max Activating Token Index: 551

Text #14

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.8964. Min Act: -0.0000

Data Index: 72559 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.9236. Min Act: -0.0000

Data Index: 530258 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.8916. Min Act: -0.0000

Data Index: 99349 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.8900. Min Act: -0.0000

Data Index: 589963 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.8440. Min Act: -0.0000

Data Index: 1169225 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 2.8615. Min Range: -2.8615

Max Act: 1.6706. Min Act: -0.0000

Data Index: 1167842 (C4 (Web Text))

Max Activating Token Index: 77