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

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

Neuron 181 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2360. Min Act: -0.0002

Data Index: 1562072 (Python Code)

Max Activating Token Index: 920

Text #1

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2349. Min Act: -0.0002

Data Index: 1599666 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2139. Min Act: -0.0002

Data Index: 1508881 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2156. Min Act: -0.0002

Data Index: 1552833 (Python Code)

Max Activating Token Index: 405

Text #4

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2181. Min Act: -0.0002

Data Index: 1545447 (Python Code)

Max Activating Token Index: 760

Text #5

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2105. Min Act: -0.0002

Data Index: 1502921 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2090. Min Act: -0.0002

Data Index: 1391105 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2112. Min Act: -0.0002

Data Index: 1404703 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2094. Min Act: -0.0002

Data Index: 1451233 (Python Code)

Max Activating Token Index: 199

Text #9

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2075. Min Act: -0.0002

Data Index: 1579615 (Python Code)

Max Activating Token Index: 747

Text #10

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2095. Min Act: -0.0002

Data Index: 1537641 (Python Code)

Max Activating Token Index: 585

Text #11

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2040. Min Act: -0.0002

Data Index: 1511518 (Python Code)

Max Activating Token Index: 186

Text #12

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2019. Min Act: -0.0002

Data Index: 1537830 (Python Code)

Max Activating Token Index: 744

Text #13

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2029. Min Act: -0.0002

Data Index: 1588531 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2022. Min Act: -0.0002

Data Index: 1569531 (Python Code)

Max Activating Token Index: 273

Text #15

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1995. Min Act: -0.0002

Data Index: 1652324 (Python Code)

Max Activating Token Index: 266

Text #16

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1978. Min Act: -0.0002

Data Index: 1600609 (Python Code)

Max Activating Token Index: 499

Text #17

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1978. Min Act: -0.0002

Data Index: 1638696 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1985. Min Act: -0.0002

Data Index: 1584986 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1983. Min Act: -0.0002

Data Index: 1463153 (Python Code)

Max Activating Token Index: 763