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

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

Neuron 5842 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.9202. Min Act: -0.0001

Data Index: 976708 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1542904 (Python Code)

Max Activating Token Index: 657

Text #2

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.8141. Min Act: -0.0001

Data Index: 1489343 (Python Code)

Max Activating Token Index: 776

Text #3

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7477. Min Act: -0.0001

Data Index: 1440051 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7961. Min Act: -0.0001

Data Index: 1648391 (Python Code)

Max Activating Token Index: 846

Text #5

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7177. Min Act: -0.0001

Data Index: 1646980 (Python Code)

Max Activating Token Index: 28

Text #6

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1035221 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6785. Min Act: -0.0001

Data Index: 957526 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7143. Min Act: -0.0000

Data Index: 1650027 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6730. Min Act: -0.0000

Data Index: 851056 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1573828 (Python Code)

Max Activating Token Index: 703

Text #11

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1468681 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7245. Min Act: -0.0001

Data Index: 1522541 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6028. Min Act: -0.0001

Data Index: 1442954 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.7006. Min Act: -0.0000

Data Index: 1154460 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6653. Min Act: -0.0000

Data Index: 882613 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1649055 (Python Code)

Max Activating Token Index: 41

Text #17

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1281585 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.6547. Min Act: -0.0001

Data Index: 1489048 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 0.9202. Min Range: -0.9202

Max Act: 0.5934. Min Act: -0.0001

Data Index: 1366802 (Python Code)

Max Activating Token Index: 33