Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1334 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2468. Min Act: -0.0001

Data Index: 915447 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2418. Min Act: -0.0001

Data Index: 473877 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1231399 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2258. Min Act: -0.0001

Data Index: 951270 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2150. Min Act: -0.0001

Data Index: 639999 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2156. Min Act: -0.0001

Data Index: 312011 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2090. Min Act: -0.0001

Data Index: 600184 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2031. Min Act: -0.0001

Data Index: 349099 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1984. Min Act: -0.0001

Data Index: 892171 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1992. Min Act: -0.0001

Data Index: 754310 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1940. Min Act: -0.0001

Data Index: 303089 (C4 (Web Text))

Max Activating Token Index: 812

Text #11

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1918. Min Act: -0.0001

Data Index: 472689 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1992. Min Act: -0.0001

Data Index: 1256009 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1867. Min Act: -0.0001

Data Index: 829886 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1872. Min Act: -0.0001

Data Index: 1072576 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.2021. Min Act: -0.0001

Data Index: 792473 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1752. Min Act: -0.0001

Data Index: 563276 (C4 (Web Text))

Max Activating Token Index: 739

Text #17

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1796. Min Act: -0.0001

Data Index: 456938 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1956. Min Act: -0.0001

Data Index: 519496 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.2468. Min Range: -0.2468

Max Act: 0.1835. Min Act: -0.0001

Data Index: 841207 (C4 (Web Text))

Max Activating Token Index: 691