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

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

Neuron 842 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.9919. Min Act: -0.0000

Data Index: 1025197 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 2.0564. Min Range: -2.0564

Max Act: 2.0564. Min Act: -0.0000

Data Index: 590288 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.8791. Min Act: -0.0000

Data Index: 1051433 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.9841. Min Act: -0.0000

Data Index: 636482 (C4 (Web Text))

Max Activating Token Index: 733

Text #4

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1617018 (Python Code)

Max Activating Token Index: 536

Text #5

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.7551. Min Act: -0.0000

Data Index: 903377 (C4 (Web Text))

Max Activating Token Index: 293

Text #6

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1642132 (Python Code)

Max Activating Token Index: 252

Text #7

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.7207. Min Act: -0.0000

Data Index: 936414 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.6656. Min Act: -0.0000

Data Index: 1207994 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.7156. Min Act: -0.0000

Data Index: 1242046 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.6108. Min Act: -0.0000

Data Index: 178660 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.6080. Min Act: -0.0000

Data Index: 105902 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.5735. Min Act: -0.0000

Data Index: 864927 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1311956 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.6429. Min Act: -0.0000

Data Index: 364650 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.5523. Min Act: -0.0000

Data Index: 547559 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1316823 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.4195. Min Act: -0.0000

Data Index: 1179504 (C4 (Web Text))

Max Activating Token Index: 345

Text #18

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1417531 (Python Code)

Max Activating Token Index: 571

Text #19

Max Range: 2.0564. Min Range: -2.0564

Max Act: 1.4973. Min Act: -0.0000

Data Index: 645056 (C4 (Web Text))

Max Activating Token Index: 445