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

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

Neuron 3647 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.3537. Min Act: -0.0000

Data Index: 127012 (C4 (Web Text))

Max Activating Token Index: 512

Text #1

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.2621. Min Act: -0.0000

Data Index: 322467 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.2332. Min Act: -0.0000

Data Index: 379834 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.1892. Min Act: -0.0000

Data Index: 426813 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1181370 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.0838. Min Act: -0.0000

Data Index: 211942 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.1345. Min Act: -0.0000

Data Index: 3810 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1013925 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.0384. Min Act: -0.0000

Data Index: 453581 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 1.3537. Min Range: -1.3537

Max Act: 1.0155. Min Act: -0.0000

Data Index: 84486 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.9377. Min Act: -0.0000

Data Index: 724419 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.9243. Min Act: -0.0000

Data Index: 336372 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.9667. Min Act: -0.0000

Data Index: 70673 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1330596 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.8533. Min Act: -0.0000

Data Index: 104594 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.9016. Min Act: -0.0000

Data Index: 349845 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.8208. Min Act: -0.0000

Data Index: 1110226 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.8535. Min Act: -0.0000

Data Index: 1075971 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.8413. Min Act: -0.0000

Data Index: 266252 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 1.3537. Min Range: -1.3537

Max Act: 0.8327. Min Act: -0.0000

Data Index: 597177 (C4 (Web Text))

Max Activating Token Index: 383