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

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

Neuron 5936 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0170. Min Range: -2.0170

Max Act: 2.0135. Min Act: -0.0000

Data Index: 1435122 (Python Code)

Max Activating Token Index: 621

Text #1

Max Range: 2.0170. Min Range: -2.0170

Max Act: 2.0170. Min Act: -0.0000

Data Index: 1616096 (Python Code)

Max Activating Token Index: 525

Text #2

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.8485. Min Act: -0.0000

Data Index: 1527644 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.7299. Min Act: -0.0000

Data Index: 300407 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.8307. Min Act: -0.0000

Data Index: 9416 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.7815. Min Act: -0.0000

Data Index: 292705 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.7709. Min Act: -0.0000

Data Index: 267740 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1534586 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.7431. Min Act: -0.0000

Data Index: 1004175 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.7519. Min Act: -0.0000

Data Index: 1070314 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6445. Min Act: -0.0000

Data Index: 1440778 (Python Code)

Max Activating Token Index: 260

Text #11

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1380310 (Python Code)

Max Activating Token Index: 84

Text #12

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.7242. Min Act: -0.0000

Data Index: 811978 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.7916. Min Act: -0.0000

Data Index: 618914 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6739. Min Act: -0.0000

Data Index: 1520055 (Python Code)

Max Activating Token Index: 1008

Text #15

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6711. Min Act: -0.0000

Data Index: 1590917 (Python Code)

Max Activating Token Index: 103

Text #16

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.5804. Min Act: -0.0000

Data Index: 1561429 (Python Code)

Max Activating Token Index: 35

Text #17

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1600878 (Python Code)

Max Activating Token Index: 276

Text #18

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6448. Min Act: -0.0000

Data Index: 1593601 (Python Code)

Max Activating Token Index: 157

Text #19

Max Range: 2.0170. Min Range: -2.0170

Max Act: 1.6414. Min Act: -0.0000

Data Index: 1550118 (Python Code)

Max Activating Token Index: 196