Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1590 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6330. Min Range: -2.6330

Max Act: 2.6330. Min Act: -0.0000

Data Index: 730120 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.9941. Min Act: -0.0000

Data Index: 433349 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.7246. Min Act: -0.0000

Data Index: 703472 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.4898. Min Act: -0.0000

Data Index: 1009641 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.3465. Min Act: -0.0000

Data Index: 360708 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.3458. Min Act: -0.0000

Data Index: 441320 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.2757. Min Act: -0.0000

Data Index: 605061 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1010882 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.2252. Min Act: -0.0000

Data Index: 251046 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.2150. Min Act: -0.0000

Data Index: 581219 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1703. Min Act: -0.0000

Data Index: 209660 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1583. Min Act: -0.0000

Data Index: 782493 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.0864. Min Act: -0.0000

Data Index: 815224 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1410. Min Act: -0.0000

Data Index: 480949 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.0675. Min Act: -0.0000

Data Index: 63887 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1273. Min Act: -0.0000

Data Index: 262557 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1204. Min Act: -0.0000

Data Index: 812431 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1858. Min Act: -0.0000

Data Index: 601662 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1129. Min Act: -0.0000

Data Index: 937593 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 2.6330. Min Range: -2.6330

Max Act: 1.1062. Min Act: -0.0000

Data Index: 834124 (C4 (Web Text))

Max Activating Token Index: 101