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

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

Neuron 271 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.7485. Min Act: -0.0000

Data Index: 581373 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1032300 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6730. Min Act: -0.0000

Data Index: 676189 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.6009. Min Act: -0.0000

Data Index: 215902 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.5692. Min Act: 0.0000

Data Index: 250953 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.5581. Min Act: -0.0000

Data Index: 393602 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.5545. Min Act: -0.0000

Data Index: 841702 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.4995. Min Act: -0.0000

Data Index: 1201687 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.4397. Min Act: -0.0000

Data Index: 1249763 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.4315. Min Act: -0.0000

Data Index: 869812 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.4352. Min Act: -0.0000

Data Index: 386050 (C4 (Web Text))

Max Activating Token Index: 445

Text #11

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.4303. Min Act: -0.0000

Data Index: 815958 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1322784 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.4076. Min Act: -0.0000

Data Index: 939266 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.3943. Min Act: -0.0000

Data Index: 1106462 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1071751 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.3813. Min Act: -0.0000

Data Index: 65281 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1237682 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.3545. Min Act: -0.0000

Data Index: 36215 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.7485. Min Range: -0.7485

Max Act: 0.3813. Min Act: -0.0000

Data Index: 1270410 (C4 (Web Text))

Max Activating Token Index: 335