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

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

Neuron 4358 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: 0.9920. Min Range: -0.9920

Max Act: 0.9920. Min Act: -0.0000

Data Index: 670782 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7653. Min Act: -0.0000

Data Index: 968089 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7254. Min Act: -0.0000

Data Index: 1010595 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7314. Min Act: -0.0000

Data Index: 1073985 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6921. Min Act: -0.0000

Data Index: 207422 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6927. Min Act: -0.0000

Data Index: 972211 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1004884 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.7050. Min Act: -0.0000

Data Index: 1272489 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6616. Min Act: -0.0000

Data Index: 718517 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6507. Min Act: -0.0000

Data Index: 459000 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6484. Min Act: -0.0000

Data Index: 893431 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1076145 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6037. Min Act: -0.0000

Data Index: 522782 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6160. Min Act: -0.0000

Data Index: 404007 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6174. Min Act: -0.0000

Data Index: 680148 (C4 (Web Text))

Max Activating Token Index: 532

Text #15

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6319. Min Act: -0.0000

Data Index: 345995 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1119155 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6114. Min Act: -0.0000

Data Index: 490997 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1050955 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.9920. Min Range: -0.9920

Max Act: 0.5951. Min Act: -0.0000

Data Index: 899998 (C4 (Web Text))

Max Activating Token Index: 248