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

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

Neuron 4425 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.5075. Min Act: -0.0000

Data Index: 56273 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.5095. Min Act: -0.0000

Data Index: 665493 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1290356 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4866. Min Act: -0.0000

Data Index: 1016840 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4670. Min Act: -0.0000

Data Index: 841967 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4271. Min Act: -0.0000

Data Index: 1172683 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4124. Min Act: -0.0000

Data Index: 730469 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4107. Min Act: -0.0000

Data Index: 83421 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4221. Min Act: -0.0000

Data Index: 72032 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3961. Min Act: -0.0000

Data Index: 1011259 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3677. Min Act: -0.0000

Data Index: 756737 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4247. Min Act: -0.0000

Data Index: 564691 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3949. Min Act: -0.0000

Data Index: 809764 (C4 (Web Text))

Max Activating Token Index: 635

Text #13

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3944. Min Act: -0.0000

Data Index: 857380 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3712. Min Act: -0.0000

Data Index: 258585 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3499. Min Act: -0.0000

Data Index: 550268 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1219264 (C4 (Web Text))

Max Activating Token Index: 394

Text #17

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3571. Min Act: -0.0000

Data Index: 67515 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3539. Min Act: -0.0000

Data Index: 514577 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3510. Min Act: -0.0000

Data Index: 587217 (C4 (Web Text))

Max Activating Token Index: 438