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

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

Neuron 3751 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3426. Min Range: -4.3426

Max Act: 4.3426. Min Act: -0.0000

Data Index: 1451762 (Python Code)

Max Activating Token Index: 147

Text #1

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.4572. Min Act: -0.0000

Data Index: 1535206 (Python Code)

Max Activating Token Index: 332

Text #2

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1209725 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.1418. Min Act: -0.0000

Data Index: 1535890 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.2312. Min Act: -0.0000

Data Index: 1534911 (Python Code)

Max Activating Token Index: 143

Text #5

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.0207. Min Act: -0.0000

Data Index: 143328 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.1179. Min Act: -0.0000

Data Index: 59383 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9757. Min Act: -0.0000

Data Index: 1525978 (Python Code)

Max Activating Token Index: 644

Text #8

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9834. Min Act: -0.0000

Data Index: 371738 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.1770. Min Act: -0.0000

Data Index: 827703 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.0858. Min Act: -0.0000

Data Index: 790011 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9892. Min Act: -0.0000

Data Index: 203101 (C4 (Web Text))

Max Activating Token Index: 924

Text #12

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9655. Min Act: -0.0000

Data Index: 172178 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9574. Min Act: -0.0000

Data Index: 1032656 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.0622. Min Act: -0.0000

Data Index: 615812 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9171. Min Act: -0.0000

Data Index: 1515146 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9532. Min Act: -0.0000

Data Index: 1559841 (Python Code)

Max Activating Token Index: 254

Text #17

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.8032. Min Act: -0.0000

Data Index: 6761 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 4.3426. Min Range: -4.3426

Max Act: 2.1479. Min Act: -0.0000

Data Index: 1096758 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 4.3426. Min Range: -4.3426

Max Act: 1.9044. Min Act: -0.0000

Data Index: 464218 (C4 (Web Text))

Max Activating Token Index: 790