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

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

Neuron 1105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2808. Min Act: -0.0001

Data Index: 521944 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2787. Min Act: -0.0001

Data Index: 381298 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2288. Min Act: -0.0001

Data Index: 569053 (C4 (Web Text))

Max Activating Token Index: 740

Text #3

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2195. Min Act: -0.0001

Data Index: 178389 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2071. Min Act: -0.0001

Data Index: 1326899 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2320. Min Act: -0.0001

Data Index: 232747 (C4 (Web Text))

Max Activating Token Index: 152

Text #6

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2158. Min Act: -0.0001

Data Index: 516675 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1976. Min Act: -0.0001

Data Index: 5611 (C4 (Web Text))

Max Activating Token Index: 1016

Text #8

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2231. Min Act: -0.0001

Data Index: 802774 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2135. Min Act: -0.0001

Data Index: 314644 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2052. Min Act: -0.0001

Data Index: 41744 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1919. Min Act: -0.0001

Data Index: 981592 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1913. Min Act: -0.0001

Data Index: 998944 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1849. Min Act: -0.0001

Data Index: 755427 (C4 (Web Text))

Max Activating Token Index: 336

Text #14

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1848. Min Act: -0.0001

Data Index: 335014 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1893. Min Act: -0.0001

Data Index: 738231 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1870. Min Act: -0.0001

Data Index: 1034671 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.2190. Min Act: -0.0001

Data Index: 136718 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1847. Min Act: -0.0001

Data Index: 263037 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.2808. Min Range: -0.2808

Max Act: 0.1770. Min Act: -0.0001

Data Index: 27110 (C4 (Web Text))

Max Activating Token Index: 705