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

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

Neuron 1206 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: 0.6511. Min Range: -0.6511

Max Act: 0.6511. Min Act: 0.0000

Data Index: 591484 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.6337. Min Act: -0.0000

Data Index: 154666 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.6122. Min Act: -0.0000

Data Index: 832240 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1180428 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5774. Min Act: -0.0000

Data Index: 219763 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1039139 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5912. Min Act: -0.0000

Data Index: 896464 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5666. Min Act: -0.0000

Data Index: 1137581 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1086750 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.5731. Min Act: -0.0000

Data Index: 247669 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.4566. Min Act: -0.0000

Data Index: 648025 (C4 (Web Text))

Max Activating Token Index: 442

Text #11

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.4067. Min Act: -0.0000

Data Index: 156208 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1297853 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.3971. Min Act: -0.0000

Data Index: 676777 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.3542. Min Act: -0.0000

Data Index: 397364 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.3673. Min Act: -0.0000

Data Index: 101674 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.3435. Min Act: -0.0000

Data Index: 734240 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.3086. Min Act: -0.0000

Data Index: 435384 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.3576. Min Act: -0.0000

Data Index: 926956 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.6511. Min Range: -0.6511

Max Act: 0.3379. Min Act: -0.0000

Data Index: 935051 (C4 (Web Text))

Max Activating Token Index: 160