Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2105 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.5739. Min Act: -0.0001

Data Index: 750838 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.5006. Min Act: -0.0001

Data Index: 383074 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.3855. Min Act: -0.0001

Data Index: 121724 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.4791. Min Act: -0.0001

Data Index: 581616 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.3222. Min Act: -0.0001

Data Index: 1031462 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.4721. Min Act: -0.0001

Data Index: 1224041 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.4209. Min Act: -0.0001

Data Index: 653919 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.2984. Min Act: -0.0001

Data Index: 562947 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.2553. Min Act: -0.0001

Data Index: 485420 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.2763. Min Act: -0.0001

Data Index: 1179228 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.3171. Min Act: -0.0001

Data Index: 771729 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.3531. Min Act: -0.0001

Data Index: 878450 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.3180. Min Act: -0.0001

Data Index: 203230 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.3289. Min Act: -0.0001

Data Index: 434568 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.1870. Min Act: -0.0001

Data Index: 107263 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.2971. Min Act: -0.0001

Data Index: 1170987 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.1777. Min Act: -0.0001

Data Index: 538587 (C4 (Web Text))

Max Activating Token Index: 201

Text #17

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.2258. Min Act: -0.0001

Data Index: 1181653 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.1207. Min Act: -0.0001

Data Index: 874296 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.5739. Min Range: -1.5739

Max Act: 1.1541. Min Act: -0.0000

Data Index: 684032 (C4 (Web Text))

Max Activating Token Index: 415