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

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

Neuron 2446 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: 2.5820. Min Range: -2.5820

Max Act: 2.5820. Min Act: -0.0000

Data Index: 275832 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.2615. Min Act: -0.0000

Data Index: 1024428 (C4 (Web Text))

Max Activating Token Index: 874

Text #2

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.3651. Min Act: -0.0000

Data Index: 1150909 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.1320. Min Act: -0.0000

Data Index: 1327033 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.1263. Min Act: -0.0000

Data Index: 283984 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.2929. Min Act: -0.0000

Data Index: 655661 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.1690. Min Act: -0.0000

Data Index: 1242974 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.7419. Min Act: -0.0000

Data Index: 207446 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.0265. Min Act: -0.0000

Data Index: 1326243 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.0124. Min Act: -0.0000

Data Index: 1021221 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.9969. Min Act: -0.0000

Data Index: 691069 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.9791. Min Act: -0.0000

Data Index: 192161 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 2.5820. Min Range: -2.5820

Max Act: 2.0924. Min Act: -0.0000

Data Index: 366815 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.8559. Min Act: -0.0000

Data Index: 776773 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.9028. Min Act: -0.0000

Data Index: 995904 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.9328. Min Act: -0.0000

Data Index: 290376 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.7263. Min Act: -0.0000

Data Index: 544557 (C4 (Web Text))

Max Activating Token Index: 236

Text #17

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.8604. Min Act: -0.0000

Data Index: 798014 (C4 (Web Text))

Max Activating Token Index: 1020

Text #18

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.8448. Min Act: -0.0000

Data Index: 560589 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 2.5820. Min Range: -2.5820

Max Act: 1.6876. Min Act: -0.0000

Data Index: 1339540 (C4 (Web Text))

Max Activating Token Index: 950