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

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

Neuron 2886 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: 4.1565. Min Range: -4.1565

Max Act: 4.1108. Min Act: -0.0000

Data Index: 350375 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 4.1565. Min Range: -4.1565

Max Act: 4.1565. Min Act: -0.0000

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 4.1565. Min Range: -4.1565

Max Act: 3.4466. Min Act: -0.0000

Data Index: 755293 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 4.1565. Min Range: -4.1565

Max Act: 3.1880. Min Act: -0.0000

Data Index: 273534 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 4.1565. Min Range: -4.1565

Max Act: 3.2294. Min Act: -0.0000

Data Index: 393022 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.9810. Min Act: -0.0000

Data Index: 877595 (C4 (Web Text))

Max Activating Token Index: 808

Text #6

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.9792. Min Act: -0.0000

Data Index: 867032 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 4.1565. Min Range: -4.1565

Max Act: 3.0443. Min Act: -0.0000

Data Index: 1146381 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.9062. Min Act: -0.0000

Data Index: 1346659 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.7789. Min Act: -0.0000

Data Index: 43093 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.9217. Min Act: -0.0000

Data Index: 808400 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.7542. Min Act: -0.0000

Data Index: 661499 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.8833. Min Act: -0.0000

Data Index: 386955 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.8685. Min Act: -0.0000

Data Index: 1281225 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.8225. Min Act: -0.0000

Data Index: 160034 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.7851. Min Act: -0.0000

Data Index: 619128 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.7268. Min Act: -0.0000

Data Index: 615421 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.7433. Min Act: -0.0000

Data Index: 978154 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.6936. Min Act: -0.0000

Data Index: 53089 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 4.1565. Min Range: -4.1565

Max Act: 2.6660. Min Act: -0.0000

Data Index: 257944 (C4 (Web Text))

Max Activating Token Index: 273