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

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

Neuron 1952 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.4008. Min Act: -0.0004

Data Index: 20639 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.3873. Min Act: -0.0004

Data Index: 1221046 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.4393. Min Act: -0.0004

Data Index: 1074819 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.3081. Min Act: -0.0004

Data Index: 846832 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.3214. Min Act: -0.0004

Data Index: 1099347 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2594. Min Act: -0.0004

Data Index: 954914 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2637. Min Act: -0.0004

Data Index: 818566 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.3029. Min Act: -0.0004

Data Index: 245723 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1864. Min Act: -0.0004

Data Index: 670212 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2223. Min Act: -0.0004

Data Index: 338529 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2544. Min Act: -0.0004

Data Index: 370983 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2676. Min Act: -0.0004

Data Index: 273893 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1265. Min Act: -0.0004

Data Index: 999258 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2627. Min Act: -0.0004

Data Index: 416231 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1719. Min Act: -0.0004

Data Index: 918477 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1710. Min Act: -0.0004

Data Index: 663142 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1385. Min Act: -0.0004

Data Index: 490691 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2103. Min Act: -0.0004

Data Index: 990412 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2231. Min Act: -0.0004

Data Index: 598494 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2730. Min Act: -0.0004

Data Index: 94337 (C4 (Web Text))

Max Activating Token Index: 181