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

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

Neuron 4728 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: 1.7416. Min Range: -1.7416

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1329617 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.3907. Min Act: -0.0000

Data Index: 1342087 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.7416. Min Act: -0.0000

Data Index: 376338 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.5016. Min Act: -0.0000

Data Index: 1068301 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.6570. Min Act: -0.0000

Data Index: 1344803 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.5395. Min Act: -0.0000

Data Index: 1016770 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.4935. Min Act: -0.0000

Data Index: 853084 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.2626. Min Act: -0.0000

Data Index: 383443 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.4030. Min Act: -0.0000

Data Index: 805052 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.2104. Min Act: -0.0000

Data Index: 258081 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1606655 (Python Code)

Max Activating Token Index: 529

Text #11

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.4252. Min Act: -0.0001

Data Index: 462816 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.2937. Min Act: -0.0000

Data Index: 1328465 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.3717. Min Act: -0.0000

Data Index: 3622 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.2768. Min Act: -0.0000

Data Index: 961906 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.5851. Min Act: -0.0000

Data Index: 1531413 (Python Code)

Max Activating Token Index: 466

Text #16

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1350351 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.1838. Min Act: -0.0000

Data Index: 526085 (C4 (Web Text))

Max Activating Token Index: 721

Text #18

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.1614. Min Act: -0.0000

Data Index: 347598 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 1.7416. Min Range: -1.7416

Max Act: 1.3357. Min Act: -0.0000

Data Index: 810180 (C4 (Web Text))

Max Activating Token Index: 292