Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2678 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.2263. Min Act: -0.0000

Data Index: 764302 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 1.2263. Min Range: -1.2263

Max Act: 1.0192. Min Act: -0.0000

Data Index: 838819 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9733. Min Act: -0.0000

Data Index: 1098154 (C4 (Web Text))

Max Activating Token Index: 328

Text #3

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1349967 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9408. Min Act: -0.0000

Data Index: 987246 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8933. Min Act: -0.0000

Data Index: 606412 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9832. Min Act: -0.0000

Data Index: 718903 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8774. Min Act: -0.0000

Data Index: 989022 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1073465 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8446. Min Act: -0.0000

Data Index: 496778 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1148083 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7877. Min Act: -0.0000

Data Index: 449855 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8034. Min Act: -0.0000

Data Index: 329362 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8049. Min Act: -0.0000

Data Index: 981356 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.8576. Min Act: -0.0000

Data Index: 264420 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1203161 (C4 (Web Text))

Max Activating Token Index: 280

Text #16

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7482. Min Act: -0.0000

Data Index: 683271 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7437. Min Act: -0.0000

Data Index: 193960 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7091. Min Act: -0.0000

Data Index: 214478 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.2263. Min Range: -1.2263

Max Act: 0.7361. Min Act: -0.0000

Data Index: 338407 (C4 (Web Text))

Max Activating Token Index: 215