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

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

Neuron 3516 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1854. Min Range: -6.1854

Max Act: 6.1854. Min Act: -0.0000

Data Index: 649455 (C4 (Web Text))

Max Activating Token Index: 371

Text #1

Max Range: 6.1854. Min Range: -6.1854

Max Act: 5.7135. Min Act: -0.0000

Data Index: 1010546 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 6.1854. Min Range: -6.1854

Max Act: 5.6795. Min Act: -0.0000

Data Index: 318226 (C4 (Web Text))

Max Activating Token Index: 637

Text #3

Max Range: 6.1854. Min Range: -6.1854

Max Act: 5.0741. Min Act: -0.0000

Data Index: 314991 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.8424. Min Act: -0.0000

Data Index: 1350920 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.9767. Min Act: -0.0000

Data Index: 1351413 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.4537. Min Act: -0.0000

Data Index: 257174 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.8198. Min Act: -0.0000

Data Index: 465063 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.5190. Min Act: -0.0000

Data Index: 355367 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.7500. Min Act: -0.0000

Data Index: 12378 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.4146. Min Act: -0.0000

Data Index: 1201838 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.4626. Min Act: -0.0000

Data Index: 116029 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.6041. Min Act: -0.0000

Data Index: 906109 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.3838. Min Act: -0.0000

Data Index: 340842 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.3504. Min Act: -0.0000

Data Index: 1265275 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.7068. Min Act: -0.0000

Data Index: 750280 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.4697. Min Act: -0.0000

Data Index: 878861 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.1871. Min Act: -0.0000

Data Index: 280871 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.4353. Min Act: -0.0000

Data Index: 345589 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 6.1854. Min Range: -6.1854

Max Act: 4.3357. Min Act: -0.0000

Data Index: 726375 (C4 (Web Text))

Max Activating Token Index: 78