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

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

Neuron 3900 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: 0.3464. Min Range: -0.3464

Max Act: 0.3464. Min Act: -0.0000

Data Index: 484423 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2808. Min Act: -0.0000

Data Index: 718013 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1164332 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2488. Min Act: -0.0000

Data Index: 442186 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2493. Min Act: -0.0000

Data Index: 231020 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2277. Min Act: -0.0000

Data Index: 55538 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2319. Min Act: -0.0000

Data Index: 528241 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1829. Min Act: -0.0000

Data Index: 322476 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2110. Min Act: -0.0000

Data Index: 827703 (C4 (Web Text))

Max Activating Token Index: 513

Text #9

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2073. Min Act: -0.0000

Data Index: 187282 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1006633 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1246828 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1915. Min Act: -0.0000

Data Index: 482458 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1933. Min Act: -0.0000

Data Index: 892673 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2113. Min Act: -0.0000

Data Index: 609712 (C4 (Web Text))

Max Activating Token Index: 1018

Text #15

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1927. Min Act: -0.0000

Data Index: 516921 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1254362 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1948. Min Act: -0.0000

Data Index: 663214 (C4 (Web Text))

Max Activating Token Index: 119

Text #18

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1961. Min Act: -0.0000

Data Index: 966617 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.3464. Min Range: -0.3464

Max Act: 0.1832. Min Act: -0.0000

Data Index: 767106 (C4 (Web Text))

Max Activating Token Index: 382