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

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

Neuron 1752 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7590. Min Range: -3.7590

Max Act: 3.7590. Min Act: -0.0000

Data Index: 698342 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.7787. Min Act: -0.0000

Data Index: 1322494 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.6931. Min Act: -0.0000

Data Index: 999660 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.5059. Min Act: -0.0000

Data Index: 1146840 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.7327. Min Act: -0.0000

Data Index: 536480 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.4386. Min Act: -0.0000

Data Index: 72910 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.3619. Min Act: -0.0000

Data Index: 487316 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.3140. Min Act: -0.0000

Data Index: 231967 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.2551. Min Act: -0.0000

Data Index: 1171055 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.0651. Min Act: -0.0000

Data Index: 702679 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.1597. Min Act: -0.0000

Data Index: 11435 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.0923. Min Act: -0.0000

Data Index: 891937 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 3.7590. Min Range: -3.7590

Max Act: 1.9211. Min Act: -0.0000

Data Index: 723133 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 3.7590. Min Range: -3.7590

Max Act: 1.9197. Min Act: -0.0000

Data Index: 383433 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 3.7590. Min Range: -3.7590

Max Act: 1.9976. Min Act: -0.0000

Data Index: 1343952 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 3.7590. Min Range: -3.7590

Max Act: 2.0887. Min Act: -0.0000

Data Index: 1224144 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 3.7590. Min Range: -3.7590

Max Act: 1.8831. Min Act: -0.0000

Data Index: 503541 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 3.7590. Min Range: -3.7590

Max Act: 1.9526. Min Act: -0.0000

Data Index: 150244 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 3.7590. Min Range: -3.7590

Max Act: 1.9442. Min Act: -0.0000

Data Index: 926839 (C4 (Web Text))

Max Activating Token Index: 27

Text #19

Max Range: 3.7590. Min Range: -3.7590

Max Act: 1.8508. Min Act: -0.0000

Data Index: 383444 (C4 (Web Text))

Max Activating Token Index: 112