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

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

Neuron 1963 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: 0.9237. Min Range: -0.9237

Max Act: 0.9237. Min Act: -0.0000

Data Index: 627557 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.8438. Min Act: -0.0000

Data Index: 601214 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.7345. Min Act: -0.0000

Data Index: 955275 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5622. Min Act: -0.0000

Data Index: 265300 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5359. Min Act: -0.0000

Data Index: 991448 (C4 (Web Text))

Max Activating Token Index: 991

Text #5

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5440. Min Act: -0.0000

Data Index: 985319 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5212. Min Act: -0.0000

Data Index: 796943 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4980. Min Act: -0.0000

Data Index: 392648 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5029. Min Act: -0.0000

Data Index: 1188431 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5199. Min Act: -0.0000

Data Index: 1247445 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5314. Min Act: -0.0000

Data Index: 257051 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5229. Min Act: -0.0000

Data Index: 683386 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1071146 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.5101. Min Act: -0.0000

Data Index: 263529 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4922. Min Act: -0.0000

Data Index: 994012 (C4 (Web Text))

Max Activating Token Index: 260

Text #15

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4689. Min Act: -0.0000

Data Index: 582680 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4661. Min Act: -0.0000

Data Index: 470705 (C4 (Web Text))

Max Activating Token Index: 102

Text #17

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4485. Min Act: -0.0000

Data Index: 889193 (C4 (Web Text))

Max Activating Token Index: 229

Text #18

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4621. Min Act: -0.0000

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 0.9237. Min Range: -0.9237

Max Act: 0.4274. Min Act: -0.0000

Data Index: 1142070 (C4 (Web Text))

Max Activating Token Index: 97