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

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

Neuron 4567 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0678. Min Range: -2.0678

Max Act: 2.0678. Min Act: -0.0000

Data Index: 546917 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.3119. Min Act: -0.0000

Data Index: 839407 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.1465. Min Act: -0.0000

Data Index: 1030434 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.1026. Min Act: -0.0000

Data Index: 888391 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.0984. Min Act: -0.0000

Data Index: 646402 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1059835 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9978. Min Act: -0.0000

Data Index: 1297374 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.0149. Min Act: -0.0000

Data Index: 1094002 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1632669 (Python Code)

Max Activating Token Index: 310

Text #9

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9486. Min Act: -0.0000

Data Index: 402256 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.0259. Min Act: -0.0000

Data Index: 1097452 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.1270. Min Act: -0.0000

Data Index: 251617 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 2.0678. Min Range: -2.0678

Max Act: 1.0082. Min Act: -0.0000

Data Index: 1243053 (C4 (Web Text))

Max Activating Token Index: 862

Text #13

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9543. Min Act: -0.0000

Data Index: 399052 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9020. Min Act: -0.0000

Data Index: 385864 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9588. Min Act: -0.0000

Data Index: 114646 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1394370 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9233. Min Act: -0.0000

Data Index: 1035336 (C4 (Web Text))

Max Activating Token Index: 614

Text #18

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9447. Min Act: -0.0000

Data Index: 212278 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 2.0678. Min Range: -2.0678

Max Act: 0.9486. Min Act: -0.0000

Data Index: 108385 (C4 (Web Text))

Max Activating Token Index: 886