Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1939 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2350. Min Act: -0.0003

Data Index: 1295064 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2031. Min Act: -0.0003

Data Index: 921516 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.2064. Min Act: -0.0003

Data Index: 140876 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1995. Min Act: -0.0003

Data Index: 147624 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1872. Min Act: -0.0002

Data Index: 645412 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1867. Min Act: -0.0003

Data Index: 315960 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1781. Min Act: -0.0003

Data Index: 570200 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1839. Min Act: -0.0003

Data Index: 614835 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1790. Min Act: -0.0003

Data Index: 9422 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1695. Min Act: -0.0003

Data Index: 904046 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1702. Min Act: -0.0003

Data Index: 47942 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1642. Min Act: -0.0003

Data Index: 819221 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1640. Min Act: -0.0003

Data Index: 145159 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1626. Min Act: -0.0003

Data Index: 387196 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1495. Min Act: -0.0003

Data Index: 1051912 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1599. Min Act: -0.0003

Data Index: 580969 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1489. Min Act: -0.0003

Data Index: 635494 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1659. Min Act: -0.0003

Data Index: 676565 (C4 (Web Text))

Max Activating Token Index: 918

Text #18

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1598. Min Act: -0.0002

Data Index: 567123 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.2350. Min Range: -0.2350

Max Act: 0.1592. Min Act: -0.0003

Data Index: 58976 (C4 (Web Text))

Max Activating Token Index: 815