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

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

Neuron 725 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: 0.7123. Min Range: -0.7123

Max Act: 0.7123. Min Act: -0.0000

Data Index: 287690 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1238412 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1210602 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1404575 (Python Code)

Max Activating Token Index: 328

Text #4

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.6340. Min Act: -0.0000

Data Index: 302822 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5611. Min Act: -0.0000

Data Index: 25701 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5531. Min Act: -0.0000

Data Index: 910116 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5473. Min Act: -0.0000

Data Index: 718235 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1132140 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5125. Min Act: -0.0000

Data Index: 196981 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1359680 (C4 (Web Text))

Max Activating Token Index: 405

Text #11

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5457. Min Act: -0.0000

Data Index: 467972 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5066. Min Act: -0.0000

Data Index: 282425 (C4 (Web Text))

Max Activating Token Index: 412

Text #13

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5220. Min Act: -0.0000

Data Index: 739894 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.4806. Min Act: -0.0000

Data Index: 233897 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5069. Min Act: -0.0000

Data Index: 861261 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5058. Min Act: -0.0000

Data Index: 1347691 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1491187 (Python Code)

Max Activating Token Index: 821

Text #18

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5025. Min Act: -0.0000

Data Index: 807553 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 0.7123. Min Range: -0.7123

Max Act: 0.5013. Min Act: -0.0000

Data Index: 546370 (C4 (Web Text))

Max Activating Token Index: 495