Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3080 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6332. Min Range: -2.6332

Max Act: 2.6332. Min Act: -0.0000

Data Index: 278610 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.8860. Min Act: -0.0000

Data Index: 1051979 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1421784 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.7675. Min Act: -0.0000

Data Index: 1365751 (Python Code)

Max Activating Token Index: 100

Text #4

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.7454. Min Act: -0.0000

Data Index: 1471605 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.5899. Min Act: -0.0000

Data Index: 1485512 (Python Code)

Max Activating Token Index: 554

Text #6

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.5808. Min Act: -0.0000

Data Index: 1605013 (Python Code)

Max Activating Token Index: 563

Text #7

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.4730. Min Act: -0.0000

Data Index: 1491811 (Python Code)

Max Activating Token Index: 186

Text #8

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.3638. Min Act: -0.0000

Data Index: 1627629 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.5419. Min Act: -0.0000

Data Index: 1560124 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.3039. Min Act: -0.0000

Data Index: 937056 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.2233. Min Act: -0.0000

Data Index: 787242 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1597795 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1408084 (Python Code)

Max Activating Token Index: 719

Text #14

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1164080 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.0586. Min Act: -0.0000

Data Index: 474646 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.1445. Min Act: -0.0000

Data Index: 953329 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.0313. Min Act: -0.0000

Data Index: 924087 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 2.6332. Min Range: -2.6332

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1379668 (Python Code)

Max Activating Token Index: 644

Text #19

Max Range: 2.6332. Min Range: -2.6332

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1196855 (C4 (Web Text))

Max Activating Token Index: 749