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

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

Neuron 498 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: 2.0232. Min Range: -2.0232

Max Act: 2.0232. Min Act: -0.0000

Data Index: 433914 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.9343. Min Act: -0.0000

Data Index: 408764 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.7946. Min Act: -0.0000

Data Index: 441312 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.7326. Min Act: -0.0000

Data Index: 894048 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.6889. Min Act: -0.0000

Data Index: 222049 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1041342 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4917. Min Act: -0.0000

Data Index: 691169 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4756. Min Act: -0.0000

Data Index: 638422 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4688. Min Act: -0.0000

Data Index: 1275858 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.5484. Min Act: -0.0000

Data Index: 291354 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4409. Min Act: -0.0000

Data Index: 346371 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1073658 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4462. Min Act: -0.0000

Data Index: 299049 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1234674 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3985. Min Act: -0.0000

Data Index: 912469 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1226336 (C4 (Web Text))

Max Activating Token Index: 64

Text #16

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3947. Min Act: -0.0000

Data Index: 826563 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3766. Min Act: -0.0000

Data Index: 156426 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1236568 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 2.0232. Min Range: -2.0232

Max Act: 1.3781. Min Act: -0.0000

Data Index: 1318997 (C4 (Web Text))

Max Activating Token Index: 573