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

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

Neuron 2406 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8565. Min Range: -5.8565

Max Act: 5.8565. Min Act: -0.0000

Data Index: 720306 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.8804. Min Act: -0.0000

Data Index: 1045553 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 5.8565. Min Range: -5.8565

Max Act: 4.2925. Min Act: -0.0000

Data Index: 1448423 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.9371. Min Act: -0.0000

Data Index: 343967 (C4 (Web Text))

Max Activating Token Index: 35

Text #4

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.9232. Min Act: -0.0000

Data Index: 1108477 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.7449. Min Act: -0.0000

Data Index: 1046706 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.6382. Min Act: -0.0000

Data Index: 1535642 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.8067. Min Act: -0.0000

Data Index: 1653274 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.4229. Min Act: -0.0000

Data Index: 1623790 (Python Code)

Max Activating Token Index: 208

Text #9

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.6056. Min Act: -0.0000

Data Index: 1608073 (Python Code)

Max Activating Token Index: 460

Text #10

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.5921. Min Act: -0.0000

Data Index: 1183159 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.5821. Min Act: -0.0000

Data Index: 426424 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.5544. Min Act: -0.0000

Data Index: 542452 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.4009. Min Act: -0.0000

Data Index: 1405842 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.4198. Min Act: -0.0000

Data Index: 704698 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.3920. Min Act: -0.0000

Data Index: 469954 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.3049. Min Act: -0.0000

Data Index: 385904 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.3350. Min Act: -0.0000

Data Index: 774597 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.5481. Min Act: -0.0000

Data Index: 860083 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 5.8565. Min Range: -5.8565

Max Act: 3.1219. Min Act: -0.0000

Data Index: 233659 (C4 (Web Text))

Max Activating Token Index: 795