Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3591 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1114583 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.2032. Min Act: -0.0001

Data Index: 55055 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1993. Min Act: -0.0000

Data Index: 950747 (C4 (Web Text))

Max Activating Token Index: 470

Text #3

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1823. Min Act: -0.0001

Data Index: 119711 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1891. Min Act: -0.0001

Data Index: 275772 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1352115 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1788. Min Act: -0.0001

Data Index: 384202 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1838. Min Act: -0.0001

Data Index: 22448 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1770. Min Act: -0.0001

Data Index: 19297 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1590. Min Act: -0.0000

Data Index: 43757 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1744. Min Act: -0.0000

Data Index: 618935 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1675. Min Act: -0.0000

Data Index: 381353 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1641. Min Act: -0.0001

Data Index: 1431959 (Python Code)

Max Activating Token Index: 965

Text #13

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1678. Min Act: -0.0000

Data Index: 928387 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1191622 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1681. Min Act: -0.0001

Data Index: 467402 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1610. Min Act: -0.0000

Data Index: 1585143 (Python Code)

Max Activating Token Index: 985

Text #17

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1616. Min Act: -0.0001

Data Index: 606859 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1721. Min Act: -0.0001

Data Index: 270038 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.2239. Min Range: -0.2239

Max Act: 0.1682. Min Act: -0.0000

Data Index: 125098 (C4 (Web Text))

Max Activating Token Index: 966