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

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

Neuron 2772 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1612. Min Range: -1.1612

Max Act: 1.0641. Min Act: -0.0000

Data Index: 940234 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.9968. Min Act: -0.0000

Data Index: 184326 (C4 (Web Text))

Max Activating Token Index: 222

Text #2

Max Range: 1.1612. Min Range: -1.1612

Max Act: 1.1612. Min Act: -0.0000

Data Index: 449259 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8641. Min Act: -0.0000

Data Index: 902952 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8366. Min Act: -0.0000

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8019. Min Act: -0.0000

Data Index: 792480 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1155891 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7692. Min Act: -0.0000

Data Index: 198126 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1099809 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.6698. Min Act: -0.0000

Data Index: 764620 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8106. Min Act: -0.0000

Data Index: 139087 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7950. Min Act: -0.0000

Data Index: 895749 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1350794 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.8441. Min Act: -0.0000

Data Index: 485136 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7557. Min Act: -0.0000

Data Index: 1135329 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1201462 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7105. Min Act: -0.0000

Data Index: 750056 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7833. Min Act: -0.0000

Data Index: 432237 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1088386 (C4 (Web Text))

Max Activating Token Index: 271

Text #19

Max Range: 1.1612. Min Range: -1.1612

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1190391 (C4 (Web Text))

Max Activating Token Index: 652