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

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

Neuron 5780 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: 4.3868. Min Range: -4.3868

Max Act: 4.3868. Min Act: -0.0000

Data Index: 463516 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.1064. Min Act: -0.0000

Data Index: 119877 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 4.3868. Min Range: -4.3868

Max Act: 4.2574. Min Act: -0.0000

Data Index: 1079272 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.8511. Min Act: 0.0000

Data Index: 688775 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.9353. Min Act: -0.0000

Data Index: 1274479 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.8917. Min Act: -0.0000

Data Index: 405735 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.5594. Min Act: -0.0000

Data Index: 569537 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.6879. Min Act: -0.0000

Data Index: 500191 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.7786. Min Act: -0.0000

Data Index: 702967 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.7153. Min Act: 0.0000

Data Index: 1325070 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.6949. Min Act: -0.0000

Data Index: 171198 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.6125. Min Act: -0.0000

Data Index: 489786 (C4 (Web Text))

Max Activating Token Index: 879

Text #12

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.2390. Min Act: -0.0000

Data Index: 495129 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.3282. Min Act: -0.0000

Data Index: 167792 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.1592. Min Act: -0.0000

Data Index: 503558 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.2862. Min Act: -0.0000

Data Index: 582468 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.4095. Min Act: -0.0000

Data Index: 367919 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.2444. Min Act: -0.0000

Data Index: 1324552 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.1015. Min Act: -0.0000

Data Index: 100675 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 4.3868. Min Range: -4.3868

Max Act: 3.2191. Min Act: -0.0000

Data Index: 648196 (C4 (Web Text))

Max Activating Token Index: 850