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

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

Neuron 12 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: 0.5797. Min Range: -0.5797

Max Act: 0.5797. Min Act: -0.0001

Data Index: 77206 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.5488. Min Act: -0.0001

Data Index: 765608 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4590. Min Act: -0.0001

Data Index: 116695 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4640. Min Act: -0.0001

Data Index: 840808 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4774. Min Act: -0.0001

Data Index: 1112777 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4351. Min Act: -0.0000

Data Index: 283545 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4527. Min Act: -0.0000

Data Index: 824696 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4574. Min Act: -0.0001

Data Index: 707917 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4325. Min Act: -0.0001

Data Index: 416917 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4236. Min Act: -0.0001

Data Index: 1256763 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4377. Min Act: -0.0001

Data Index: 743916 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4021. Min Act: -0.0001

Data Index: 797569 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4184. Min Act: -0.0001

Data Index: 955232 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4330. Min Act: -0.0000

Data Index: 307992 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4099. Min Act: -0.0001

Data Index: 1185692 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.3983. Min Act: -0.0001

Data Index: 403525 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4230. Min Act: -0.0001

Data Index: 973764 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4052. Min Act: -0.0001

Data Index: 1280619 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4047. Min Act: -0.0001

Data Index: 1042158 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.5797. Min Range: -0.5797

Max Act: 0.4058. Min Act: -0.0001

Data Index: 538875 (C4 (Web Text))

Max Activating Token Index: 841