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

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

Neuron 5424 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.8737. Min Act: -0.0000

Data Index: 1622421 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1437952 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5332. Min Act: -0.0000

Data Index: 652206 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1420765 (Python Code)

Max Activating Token Index: 886

Text #4

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1443230 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4795. Min Act: -0.0000

Data Index: 1396147 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4664. Min Act: -0.0000

Data Index: 833574 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1502503 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4518. Min Act: -0.0000

Data Index: 508939 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4302. Min Act: -0.0000

Data Index: 1522923 (Python Code)

Max Activating Token Index: 322

Text #10

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1216024 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4080. Min Act: -0.0000

Data Index: 484213 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1422772 (Python Code)

Max Activating Token Index: 178

Text #13

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4086. Min Act: -0.0000

Data Index: 836441 (C4 (Web Text))

Max Activating Token Index: 316

Text #14

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1649863 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4064. Min Act: -0.0000

Data Index: 1494288 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1458951 (Python Code)

Max Activating Token Index: 575

Text #17

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.3881. Min Act: -0.0000

Data Index: 1419228 (Python Code)

Max Activating Token Index: 909

Text #18

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.3756. Min Act: -0.0000

Data Index: 1513206 (Python Code)

Max Activating Token Index: 282

Text #19

Max Range: 0.8737. Min Range: -0.8737

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1449343 (Python Code)

Max Activating Token Index: 213