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

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

Neuron 4036 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1047740 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4651. Min Act: -0.0000

Data Index: 100229 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4390. Min Act: -0.0000

Data Index: 604752 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4417. Min Act: -0.0000

Data Index: 729252 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4009. Min Act: -0.0000

Data Index: 341725 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4292. Min Act: -0.0000

Data Index: 541596 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4407. Min Act: -0.0000

Data Index: 866550 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3817. Min Act: -0.0000

Data Index: 1318708 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1194720 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.4072. Min Act: -0.0000

Data Index: 284716 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3854. Min Act: -0.0000

Data Index: 190873 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3366. Min Act: -0.0000

Data Index: 341939 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1020430 (C4 (Web Text))

Max Activating Token Index: 500

Text #13

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3853. Min Act: -0.0000

Data Index: 968828 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3661. Min Act: -0.0000

Data Index: 767322 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3958. Min Act: -0.0000

Data Index: 678609 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3776. Min Act: -0.0000

Data Index: 430992 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3457. Min Act: -0.0000

Data Index: 878587 (C4 (Web Text))

Max Activating Token Index: 490

Text #18

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3747. Min Act: -0.0000

Data Index: 627184 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.5021. Min Range: -0.5021

Max Act: 0.3220. Min Act: -0.0000

Data Index: 624580 (C4 (Web Text))

Max Activating Token Index: 558