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

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

Neuron 1420 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: 2.4517. Min Range: -2.4517

Max Act: 2.4517. Min Act: -0.0000

Data Index: 306943 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.1974. Min Act: -0.0000

Data Index: 1182513 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.2098. Min Act: -0.0000

Data Index: 465335 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.2005. Min Act: -0.0000

Data Index: 429670 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.1654. Min Act: -0.0000

Data Index: 500309 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.1118. Min Act: -0.0000

Data Index: 22435 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.0642. Min Act: -0.0000

Data Index: 462365 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.0504. Min Act: -0.0000

Data Index: 802814 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.9341. Min Act: -0.0000

Data Index: 96664 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.9165. Min Act: -0.0000

Data Index: 499932 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 2.4517. Min Range: -2.4517

Max Act: 2.0211. Min Act: -0.0000

Data Index: 783525 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.8786. Min Act: -0.0000

Data Index: 494682 (C4 (Web Text))

Max Activating Token Index: 263

Text #12

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.8777. Min Act: -0.0000

Data Index: 676446 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.7697. Min Act: -0.0000

Data Index: 904079 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.9608. Min Act: -0.0000

Data Index: 710217 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.8493. Min Act: -0.0000

Data Index: 565247 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.8035. Min Act: -0.0000

Data Index: 157249 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.8898. Min Act: -0.0000

Data Index: 213300 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.6948. Min Act: -0.0000

Data Index: 144081 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 2.4517. Min Range: -2.4517

Max Act: 1.7914. Min Act: -0.0000

Data Index: 176226 (C4 (Web Text))

Max Activating Token Index: 358