Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2032 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6550. Min Act: -0.0000

Data Index: 341317 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6106. Min Act: -0.0000

Data Index: 161943 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5994. Min Act: -0.0000

Data Index: 496094 (C4 (Web Text))

Max Activating Token Index: 413

Text #3

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.6345. Min Act: -0.0000

Data Index: 658959 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5669. Min Act: -0.0000

Data Index: 481648 (C4 (Web Text))

Max Activating Token Index: 989

Text #5

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1250158 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5795. Min Act: -0.0000

Data Index: 907813 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5968. Min Act: -0.0000

Data Index: 574396 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5630. Min Act: -0.0000

Data Index: 390035 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1328793 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5349. Min Act: -0.0000

Data Index: 269461 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5148. Min Act: -0.0000

Data Index: 83588 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5314. Min Act: -0.0000

Data Index: 561534 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5283. Min Act: -0.0000

Data Index: 965831 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1345920 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.4900. Min Act: -0.0000

Data Index: 518548 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5023. Min Act: -0.0000

Data Index: 991222 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5176. Min Act: -0.0000

Data Index: 68084 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5015. Min Act: -0.0000

Data Index: 1159091 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.6550. Min Range: -0.6550

Max Act: 0.5318. Min Act: -0.0000

Data Index: 251861 (C4 (Web Text))

Max Activating Token Index: 205