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

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

Neuron 1727 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2888. Min Act: -0.0000

Data Index: 213493 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2629. Min Act: -0.0000

Data Index: 312815 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2564. Min Act: -0.0001

Data Index: 511887 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2717. Min Act: -0.0001

Data Index: 982410 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2489. Min Act: -0.0001

Data Index: 1054839 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2452. Min Act: -0.0000

Data Index: 751525 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2433. Min Act: -0.0001

Data Index: 638690 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2433. Min Act: -0.0001

Data Index: 887172 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2167. Min Act: -0.0000

Data Index: 166916 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2230. Min Act: -0.0001

Data Index: 1348476 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2241. Min Act: -0.0001

Data Index: 783700 (C4 (Web Text))

Max Activating Token Index: 224

Text #11

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2235. Min Act: -0.0000

Data Index: 714547 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2242. Min Act: -0.0001

Data Index: 325931 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2063. Min Act: -0.0000

Data Index: 711234 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.1998. Min Act: -0.0000

Data Index: 381536 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2300. Min Act: -0.0001

Data Index: 1176944 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2150. Min Act: -0.0001

Data Index: 801885 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2259. Min Act: -0.0001

Data Index: 1134666 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2214. Min Act: -0.0000

Data Index: 849151 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.2888. Min Range: -0.2888

Max Act: 0.2152. Min Act: -0.0000

Data Index: 449512 (C4 (Web Text))

Max Activating Token Index: 970