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

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

Neuron 3221 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0545. Min Act: -0.0002

Data Index: 686910 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1225923 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0508. Min Act: -0.0002

Data Index: 838392 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0509. Min Act: -0.0002

Data Index: 153940 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1042930 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0488. Min Act: -0.0002

Data Index: 24326 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0470. Min Act: -0.0002

Data Index: 410929 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0479. Min Act: -0.0002

Data Index: 170116 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0460. Min Act: -0.0002

Data Index: 99613 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1214650 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0461. Min Act: -0.0002

Data Index: 737156 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1236766 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0456. Min Act: -0.0002

Data Index: 300919 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0456. Min Act: -0.0002

Data Index: 34994 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1199459 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0433. Min Act: -0.0002

Data Index: 336868 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0439. Min Act: -0.0002

Data Index: 836869 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0438. Min Act: -0.0002

Data Index: 664171 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0437. Min Act: -0.0002

Data Index: 708773 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.0545. Min Range: -0.0545

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1068460 (C4 (Web Text))

Max Activating Token Index: 131