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

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

Neuron 4761 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1755. Min Range: -5.1755

Max Act: 5.1755. Min Act: -0.0000

Data Index: 700375 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.9508. Min Act: -0.0000

Data Index: 7386 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.7559. Min Act: -0.0000

Data Index: 892157 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.9182. Min Act: -0.0000

Data Index: 9227 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.7934. Min Act: -0.0000

Data Index: 1187853 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.7617. Min Act: -0.0000

Data Index: 1050977 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.5452. Min Act: -0.0000

Data Index: 360809 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.6833. Min Act: -0.0000

Data Index: 1271740 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.6971. Min Act: -0.0000

Data Index: 1049469 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.5746. Min Act: -0.0000

Data Index: 1061019 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.6720. Min Act: -0.0000

Data Index: 680455 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.4431. Min Act: -0.0000

Data Index: 80884 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.3243. Min Act: -0.0000

Data Index: 154554 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.5416. Min Act: -0.0000

Data Index: 584867 (C4 (Web Text))

Max Activating Token Index: 414

Text #14

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.8846. Min Act: -0.0000

Data Index: 325597 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.5034. Min Act: -0.0000

Data Index: 816053 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.3473. Min Act: -0.0000

Data Index: 962027 (C4 (Web Text))

Max Activating Token Index: 685

Text #17

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.4785. Min Act: -0.0000

Data Index: 1207266 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.3254. Min Act: -0.0000

Data Index: 1353339 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 5.1755. Min Range: -5.1755

Max Act: 3.3169. Min Act: -0.0000

Data Index: 1328813 (C4 (Web Text))

Max Activating Token Index: 598