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

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

Neuron 2049 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.6804. Min Act: -0.0000

Data Index: 133220 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.7613. Min Act: -0.0000

Data Index: 954746 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.5931. Min Act: -0.0000

Data Index: 1242615 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.3915. Min Act: -0.0000

Data Index: 546698 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.2538. Min Act: -0.0000

Data Index: 525881 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.1917. Min Act: -0.0000

Data Index: 1187336 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.1500. Min Act: -0.0000

Data Index: 63831 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.3021. Min Act: -0.0000

Data Index: 1199925 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.2764. Min Act: -0.0000

Data Index: 1173493 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.0582. Min Act: -0.0000

Data Index: 1238134 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.1518. Min Act: -0.0000

Data Index: 1116383 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.1405. Min Act: -0.0000

Data Index: 453552 (C4 (Web Text))

Max Activating Token Index: 650

Text #12

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.1223. Min Act: -0.0000

Data Index: 974509 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 3.7613. Min Range: -3.7613

Max Act: 2.9891. Min Act: -0.0000

Data Index: 1323949 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.0919. Min Act: -0.0000

Data Index: 693933 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 3.7613. Min Range: -3.7613

Max Act: 2.9220. Min Act: -0.0000

Data Index: 893493 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.0703. Min Act: -0.0000

Data Index: 626595 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.7613. Min Range: -3.7613

Max Act: 3.0260. Min Act: -0.0000

Data Index: 508801 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 3.7613. Min Range: -3.7613

Max Act: 2.8029. Min Act: -0.0000

Data Index: 1042007 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 3.7613. Min Range: -3.7613

Max Act: 2.7387. Min Act: -0.0000

Data Index: 875480 (C4 (Web Text))

Max Activating Token Index: 688