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

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

Neuron 1415 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1384. Min Range: -6.1384

Max Act: 6.1384. Min Act: -0.0000

Data Index: 320059 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 6.1384. Min Range: -6.1384

Max Act: 5.0780. Min Act: -0.0000

Data Index: 674477 (C4 (Web Text))

Max Activating Token Index: 1007

Text #2

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.9316. Min Act: -0.0000

Data Index: 1305176 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 6.1384. Min Range: -6.1384

Max Act: 5.2905. Min Act: -0.0000

Data Index: 937613 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.8468. Min Act: -0.0000

Data Index: 439567 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.1063. Min Act: -0.0000

Data Index: 641772 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.9622. Min Act: -0.0000

Data Index: 1224020 (C4 (Web Text))

Max Activating Token Index: 20

Text #7

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.5550. Min Act: -0.0000

Data Index: 1112763 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 6.1384. Min Range: -6.1384

Max Act: 3.9980. Min Act: -0.0000

Data Index: 1012287 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.3836. Min Act: -0.0000

Data Index: 1339144 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.1651. Min Act: -0.0000

Data Index: 609590 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.0908. Min Act: -0.0000

Data Index: 586187 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.0710. Min Act: -0.0000

Data Index: 451414 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.0489. Min Act: -0.0000

Data Index: 192220 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.0229. Min Act: -0.0000

Data Index: 612561 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 6.1384. Min Range: -6.1384

Max Act: 3.9253. Min Act: -0.0000

Data Index: 657196 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 6.1384. Min Range: -6.1384

Max Act: 4.0763. Min Act: -0.0000

Data Index: 1269149 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 6.1384. Min Range: -6.1384

Max Act: 3.9982. Min Act: -0.0000

Data Index: 56416 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 6.1384. Min Range: -6.1384

Max Act: 3.8201. Min Act: -0.0000

Data Index: 933556 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 6.1384. Min Range: -6.1384

Max Act: 3.6557. Min Act: -0.0000

Data Index: 1064453 (C4 (Web Text))

Max Activating Token Index: 923