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

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

Neuron 33 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.2089. Min Act: -0.0001

Data Index: 551875 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1917. Min Act: -0.0001

Data Index: 765590 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1877. Min Act: -0.0001

Data Index: 1300568 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1870. Min Act: -0.0001

Data Index: 242136 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1796. Min Act: -0.0001

Data Index: 710258 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1844. Min Act: -0.0001

Data Index: 412422 (C4 (Web Text))

Max Activating Token Index: 96

Text #6

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1912. Min Act: -0.0001

Data Index: 442244 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1706. Min Act: -0.0001

Data Index: 1272463 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1757. Min Act: -0.0001

Data Index: 774298 (C4 (Web Text))

Max Activating Token Index: 167

Text #9

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1865. Min Act: -0.0001

Data Index: 593822 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1804. Min Act: -0.0001

Data Index: 1170341 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1827. Min Act: -0.0001

Data Index: 1184225 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1788. Min Act: -0.0001

Data Index: 8571 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1272250 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1653. Min Act: -0.0001

Data Index: 698161 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1768. Min Act: -0.0001

Data Index: 3201 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1879. Min Act: -0.0001

Data Index: 939925 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1755. Min Act: -0.0001

Data Index: 715911 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1755. Min Act: -0.0001

Data Index: 131161 (C4 (Web Text))

Max Activating Token Index: 100

Text #19

Max Range: 0.2089. Min Range: -0.2089

Max Act: 0.1807. Min Act: -0.0001

Data Index: 145303 (C4 (Web Text))

Max Activating Token Index: 483