Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2959 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2448. Min Act: -0.0001

Data Index: 1351182 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1941. Min Act: -0.0001

Data Index: 301148 (C4 (Web Text))

Max Activating Token Index: 703

Text #2

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2287. Min Act: -0.0001

Data Index: 704700 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2175. Min Act: -0.0001

Data Index: 541617 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1910. Min Act: -0.0001

Data Index: 37809 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2055. Min Act: -0.0001

Data Index: 979142 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.2140. Min Act: -0.0001

Data Index: 826738 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1936. Min Act: -0.0001

Data Index: 1235431 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1796. Min Act: -0.0001

Data Index: 34479 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1826. Min Act: -0.0001

Data Index: 1238558 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1756. Min Act: -0.0001

Data Index: 930280 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1938. Min Act: -0.0001

Data Index: 701916 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1541. Min Act: -0.0001

Data Index: 192367 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1770. Min Act: -0.0001

Data Index: 955002 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1693. Min Act: -0.0001

Data Index: 263713 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1790. Min Act: -0.0001

Data Index: 989138 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1471. Min Act: -0.0001

Data Index: 1192023 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1951. Min Act: -0.0001

Data Index: 265994 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1711. Min Act: -0.0001

Data Index: 1097397 (C4 (Web Text))

Max Activating Token Index: 477

Text #19

Max Range: 0.2448. Min Range: -0.2448

Max Act: 0.1968. Min Act: -0.0001

Data Index: 983778 (C4 (Web Text))

Max Activating Token Index: 987