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

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

Neuron 3743 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.2747. Min Act: -0.0000

Data Index: 1338882 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0945. Min Act: -0.0000

Data Index: 10204 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 1.2747. Min Range: -1.2747

Max Act: 1.0063. Min Act: -0.0000

Data Index: 284180 (C4 (Web Text))

Max Activating Token Index: 632

Text #3

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9991. Min Act: -0.0000

Data Index: 180309 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9709. Min Act: -0.0000

Data Index: 764510 (C4 (Web Text))

Max Activating Token Index: 320

Text #5

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9468. Min Act: -0.0000

Data Index: 738786 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.8395. Min Act: -0.0000

Data Index: 429586 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9322. Min Act: -0.0000

Data Index: 448115 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.8676. Min Act: -0.0000

Data Index: 456678 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9741. Min Act: -0.0000

Data Index: 79401 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1320284 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9588. Min Act: -0.0000

Data Index: 383144 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9038. Min Act: -0.0000

Data Index: 672626 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.8403. Min Act: -0.0000

Data Index: 533855 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.9438. Min Act: -0.0000

Data Index: 20559 (C4 (Web Text))

Max Activating Token Index: 482

Text #15

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1077423 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.8038. Min Act: -0.0000

Data Index: 661025 (C4 (Web Text))

Max Activating Token Index: 250

Text #17

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.7941. Min Act: -0.0000

Data Index: 719560 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.7879. Min Act: -0.0000

Data Index: 1022669 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 1.2747. Min Range: -1.2747

Max Act: 0.8167. Min Act: -0.0000

Data Index: 594113 (C4 (Web Text))

Max Activating Token Index: 361