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

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

Neuron 4341 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6470. Min Range: -5.6470

Max Act: 5.6470. Min Act: -0.0000

Data Index: 568959 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 5.6470. Min Range: -5.6470

Max Act: 4.1501. Min Act: -0.0000

Data Index: 635966 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 5.6470. Min Range: -5.6470

Max Act: 4.1464. Min Act: -0.0000

Data Index: 83337 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 5.6470. Min Range: -5.6470

Max Act: 4.0570. Min Act: -0.0000

Data Index: 678165 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 5.6470. Min Range: -5.6470

Max Act: 4.1401. Min Act: -0.0001

Data Index: 1139446 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 5.6470. Min Range: -5.6470

Max Act: 4.1437. Min Act: -0.0000

Data Index: 1008920 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.5669. Min Act: -0.0001

Data Index: 38313 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.8332. Min Act: -0.0001

Data Index: 1204686 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.6044. Min Act: -0.0000

Data Index: 1352847 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.8496. Min Act: -0.0001

Data Index: 224175 (C4 (Web Text))

Max Activating Token Index: 830

Text #10

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.7114. Min Act: -0.0001

Data Index: 696358 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.2548. Min Act: -0.0000

Data Index: 1155831 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.4421. Min Act: -0.0001

Data Index: 876521 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.7361. Min Act: -0.0001

Data Index: 1021887 (C4 (Web Text))

Max Activating Token Index: 583

Text #14

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.0128. Min Act: -0.0001

Data Index: 213147 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.4437. Min Act: -0.0000

Data Index: 1002193 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.1070. Min Act: -0.0001

Data Index: 342833 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.3441. Min Act: -0.0000

Data Index: 187126 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.4595. Min Act: -0.0001

Data Index: 356835 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 5.6470. Min Range: -5.6470

Max Act: 3.7035. Min Act: -0.0000

Data Index: 322358 (C4 (Web Text))

Max Activating Token Index: 831