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

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

Neuron 2558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2799. Min Act: -0.0000

Data Index: 32330 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2418. Min Act: -0.0000

Data Index: 285313 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2391. Min Act: -0.0001

Data Index: 1427066 (Python Code)

Max Activating Token Index: 975

Text #3

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2324. Min Act: -0.0000

Data Index: 434112 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1349212 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2035. Min Act: -0.0000

Data Index: 168990 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1990. Min Act: -0.0001

Data Index: 515900 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1875. Min Act: -0.0001

Data Index: 237489 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1917. Min Act: -0.0000

Data Index: 577651 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1315643 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1952. Min Act: -0.0001

Data Index: 1008917 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.2002. Min Act: -0.0000

Data Index: 340367 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1872. Min Act: -0.0001

Data Index: 538802 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1859. Min Act: -0.0000

Data Index: 830552 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1920. Min Act: -0.0001

Data Index: 1602559 (Python Code)

Max Activating Token Index: 352

Text #15

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1792. Min Act: -0.0000

Data Index: 739148 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1744. Min Act: -0.0001

Data Index: 1300643 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1192466 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1677. Min Act: -0.0001

Data Index: 1138791 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 0.2799. Min Range: -0.2799

Max Act: 0.1808. Min Act: -0.0001

Data Index: 725969 (C4 (Web Text))

Max Activating Token Index: 588