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

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

Neuron 4642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.4559. Min Act: -0.0000

Data Index: 1054751 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1458. Min Act: -0.0000

Data Index: 576278 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.4609. Min Act: -0.0000

Data Index: 194611 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.3582. Min Act: -0.0000

Data Index: 125718 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.3441. Min Act: -0.0000

Data Index: 24168 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.3390. Min Act: -0.0000

Data Index: 1019343 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.2839. Min Act: -0.0000

Data Index: 769920 (C4 (Web Text))

Max Activating Token Index: 713

Text #7

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1900. Min Act: -0.0000

Data Index: 612611 (C4 (Web Text))

Max Activating Token Index: 938

Text #8

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.3317. Min Act: -0.0000

Data Index: 1076825 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.2008. Min Act: -0.0000

Data Index: 387919 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.3527. Min Act: -0.0000

Data Index: 684042 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1045583 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0955. Min Act: -0.0000

Data Index: 1079680 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.2022. Min Act: -0.0000

Data Index: 1319451 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.1857. Min Act: -0.0000

Data Index: 508351 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.4609. Min Range: -2.4609

Max Act: 1.9442. Min Act: -0.0000

Data Index: 460277 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.0482. Min Act: -0.0000

Data Index: 722509 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.2621. Min Act: -0.0000

Data Index: 1008782 (C4 (Web Text))

Max Activating Token Index: 1015

Text #18

Max Range: 2.4609. Min Range: -2.4609

Max Act: 1.9755. Min Act: -0.0000

Data Index: 85201 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 2.4609. Min Range: -2.4609

Max Act: 2.4269. Min Act: -0.0000

Data Index: 398710 (C4 (Web Text))

Max Activating Token Index: 742