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

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

Neuron 4713 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.8260. Min Act: -0.0000

Data Index: 509180 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.0618. Min Act: -0.0000

Data Index: 1633765 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.0388. Min Act: -0.0000

Data Index: 1604735 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1425924 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9639. Min Act: -0.0000

Data Index: 214211 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.8260. Min Range: -1.8260

Max Act: 1.0000. Min Act: -0.0000

Data Index: 611226 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9365. Min Act: -0.0000

Data Index: 159285 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9371. Min Act: -0.0000

Data Index: 282944 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9267. Min Act: 0.0000

Data Index: 21311 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.8651. Min Act: -0.0000

Data Index: 270943 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9183. Min Act: -0.0000

Data Index: 298614 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9121. Min Act: -0.0000

Data Index: 320478 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9513. Min Act: -0.0000

Data Index: 1209259 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.8922. Min Act: -0.0000

Data Index: 817285 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.8663. Min Act: -0.0000

Data Index: 447866 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.8647. Min Act: -0.0000

Data Index: 874820 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.8034. Min Act: -0.0000

Data Index: 897283 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.9055. Min Act: -0.0000

Data Index: 1220166 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.8389. Min Act: -0.0000

Data Index: 595826 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 1.8260. Min Range: -1.8260

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1627952 (Python Code)

Max Activating Token Index: 1021