Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1261 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.2604. Min Act: -0.0003

Data Index: 1568746 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.2011. Min Act: -0.0003

Data Index: 1181803 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.2156. Min Act: -0.0003

Data Index: 248271 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.1870. Min Act: -0.0003

Data Index: 1654398 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.1444. Min Act: -0.0003

Data Index: 1577708 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.1139. Min Act: -0.0003

Data Index: 1580616 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.1485. Min Act: -0.0003

Data Index: 1597395 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0826. Min Act: -0.0003

Data Index: 1412363 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0332. Min Act: -0.0003

Data Index: 556129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0233. Min Act: -0.0003

Data Index: 1458089 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0677. Min Act: -0.0003

Data Index: 1369993 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0183. Min Act: -0.0003

Data Index: 915133 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0543. Min Act: -0.0003

Data Index: 574503 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0225. Min Act: -0.0003

Data Index: 1646208 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 1.2604. Min Range: -1.2604

Max Act: 1.0017. Min Act: -0.0003

Data Index: 1330943 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9410. Min Act: -0.0003

Data Index: 1073844 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9955. Min Act: -0.0003

Data Index: 1027676 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9655. Min Act: -0.0003

Data Index: 1423657 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9780. Min Act: -0.0003

Data Index: 1441051 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 1.2604. Min Range: -1.2604

Max Act: 0.9832. Min Act: -0.0003

Data Index: 1538531 (Python Code)

Max Activating Token Index: 1023