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

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

Neuron 4303 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: 1.1923. Min Range: -1.1923

Max Act: 1.1923. Min Act: -0.0000

Data Index: 1357451 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.8962. Min Act: -0.0000

Data Index: 347680 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.7630. Min Act: -0.0000

Data Index: 782509 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.8154. Min Act: -0.0000

Data Index: 578912 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.7514. Min Act: 0.0000

Data Index: 150407 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.7864. Min Act: -0.0000

Data Index: 292009 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.7160. Min Act: 0.0000

Data Index: 957089 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1024934 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6566. Min Act: -0.0000

Data Index: 205941 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1023557 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6789. Min Act: -0.0000

Data Index: 952961 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6992. Min Act: -0.0000

Data Index: 595378 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6267. Min Act: -0.0000

Data Index: 788711 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6619. Min Act: -0.0000

Data Index: 53178 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6646. Min Act: -0.0000

Data Index: 788983 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.5843. Min Act: -0.0000

Data Index: 753339 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1533028 (Python Code)

Max Activating Token Index: 869

Text #17

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6589. Min Act: -0.0000

Data Index: 426393 (C4 (Web Text))

Max Activating Token Index: 474

Text #18

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1209517 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 1.1923. Min Range: -1.1923

Max Act: 0.6249. Min Act: -0.0000

Data Index: 437479 (C4 (Web Text))

Max Activating Token Index: 154