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

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

Neuron 4248 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.2802. Min Act: -0.0001

Data Index: 1508642 (Python Code)

Max Activating Token Index: 329

Text #1

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.1665. Min Act: -0.0001

Data Index: 1498296 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.1234. Min Act: -0.0001

Data Index: 1524502 (Python Code)

Max Activating Token Index: 543

Text #3

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.1411. Min Act: -0.0001

Data Index: 1600795 (Python Code)

Max Activating Token Index: 887

Text #4

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0400. Min Act: -0.0001

Data Index: 1592612 (Python Code)

Max Activating Token Index: 208

Text #5

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0358. Min Act: -0.0001

Data Index: 1603450 (Python Code)

Max Activating Token Index: 311

Text #6

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8992. Min Act: -0.0001

Data Index: 1554633 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 1.2802. Min Range: -1.2802

Max Act: 1.0231. Min Act: -0.0001

Data Index: 1584420 (Python Code)

Max Activating Token Index: 862

Text #8

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9179. Min Act: -0.0001

Data Index: 1577949 (Python Code)

Max Activating Token Index: 684

Text #9

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9399. Min Act: -0.0001

Data Index: 1591406 (Python Code)

Max Activating Token Index: 501

Text #10

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9074. Min Act: -0.0001

Data Index: 1528022 (Python Code)

Max Activating Token Index: 630

Text #11

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9104. Min Act: -0.0001

Data Index: 1551303 (Python Code)

Max Activating Token Index: 143

Text #12

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.9111. Min Act: -0.0001

Data Index: 1378971 (Python Code)

Max Activating Token Index: 941

Text #13

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8967. Min Act: -0.0001

Data Index: 1515181 (Python Code)

Max Activating Token Index: 65

Text #14

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8365. Min Act: -0.0001

Data Index: 1573782 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8327. Min Act: -0.0001

Data Index: 1530326 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8906. Min Act: -0.0001

Data Index: 1431008 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8564. Min Act: -0.0001

Data Index: 1464746 (Python Code)

Max Activating Token Index: 540

Text #18

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8858. Min Act: -0.0001

Data Index: 1583386 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 1.2802. Min Range: -1.2802

Max Act: 0.8817. Min Act: -0.0001

Data Index: 1649653 (Python Code)

Max Activating Token Index: 120