Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4158 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1062328 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0676. Min Act: -0.0000

Data Index: 150763 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1069749 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1034155 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0688. Min Act: -0.0000

Data Index: 39658 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0560. Min Act: -0.0000

Data Index: 290823 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0587. Min Act: -0.0000

Data Index: 270443 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0562. Min Act: -0.0000

Data Index: 37813 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1148242 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0529. Min Act: -0.0000

Data Index: 594826 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0582. Min Act: -0.0000

Data Index: 37331 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1285521 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0564. Min Act: -0.0000

Data Index: 965912 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0500. Min Act: -0.0000

Data Index: 35720 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0573. Min Act: -0.0000

Data Index: 1334573 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0513. Min Act: -0.0000

Data Index: 666930 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0496. Min Act: -0.0000

Data Index: 591639 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0500. Min Act: -0.0001

Data Index: 717400 (C4 (Web Text))

Max Activating Token Index: 316

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1065066 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0494. Min Act: -0.0000

Data Index: 921147 (C4 (Web Text))

Max Activating Token Index: 578