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

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

Neuron 4913 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.2603. Min Act: -0.0000

Data Index: 927851 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0599. Min Act: -0.0000

Data Index: 1086621 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0957. Min Act: -0.0000

Data Index: 262839 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.2603. Min Range: -1.2603

Max Act: 1.0244. Min Act: -0.0000

Data Index: 631255 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.9426. Min Act: -0.0000

Data Index: 984698 (C4 (Web Text))

Max Activating Token Index: 206

Text #5

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.9366. Min Act: -0.0000

Data Index: 1547806 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8785. Min Act: -0.0000

Data Index: 838175 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8990. Min Act: -0.0000

Data Index: 466579 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8684. Min Act: -0.0000

Data Index: 275740 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1614203 (Python Code)

Max Activating Token Index: 630

Text #10

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8568. Min Act: -0.0000

Data Index: 573847 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8204. Min Act: -0.0000

Data Index: 536775 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8677. Min Act: 0.0000

Data Index: 1191093 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1426919 (Python Code)

Max Activating Token Index: 1015

Text #14

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7669. Min Act: -0.0000

Data Index: 1033783 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8236. Min Act: -0.0000

Data Index: 359139 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.8287. Min Act: -0.0000

Data Index: 131092 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7337. Min Act: -0.0000

Data Index: 446649 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7341. Min Act: -0.0000

Data Index: 461947 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.2603. Min Range: -1.2603

Max Act: 0.7612. Min Act: -0.0000

Data Index: 856143 (C4 (Web Text))

Max Activating Token Index: 551