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

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

Neuron 4987 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.9633. Min Act: -0.0000

Data Index: 1164640 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.9911. Min Act: -0.0000

Data Index: 499103 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.8724. Min Act: -0.0000

Data Index: 283469 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.8644. Min Act: -0.0000

Data Index: 887442 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.8600. Min Act: 0.0000

Data Index: 831791 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.8491. Min Act: -0.0000

Data Index: 528046 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.8378. Min Act: -0.0000

Data Index: 207248 (C4 (Web Text))

Max Activating Token Index: 193

Text #7

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.8112. Min Act: -0.0000

Data Index: 895360 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1155409 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7779. Min Act: -0.0000

Data Index: 1206543 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7701. Min Act: -0.0000

Data Index: 94303 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7901. Min Act: -0.0000

Data Index: 104131 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7885. Min Act: -0.0000

Data Index: 300397 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.8132. Min Act: -0.0000

Data Index: 340871 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7656. Min Act: -0.0000

Data Index: 763732 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.6810. Min Act: -0.0000

Data Index: 401367 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1100220 (C4 (Web Text))

Max Activating Token Index: 390

Text #17

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.7066. Min Act: 0.0000

Data Index: 450148 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.6760. Min Act: 0.0001

Data Index: 528239 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.9911. Min Range: -0.9911

Max Act: 0.6732. Min Act: 0.0000

Data Index: 562627 (C4 (Web Text))

Max Activating Token Index: 398