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

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

Neuron 3058 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: 7.7198. Min Range: -7.7198

Max Act: 7.6971. Min Act: -0.0000

Data Index: 1596626 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 7.7198. Min Range: -7.7198

Max Act: 7.5688. Min Act: -0.0000

Data Index: 1573095 (Python Code)

Max Activating Token Index: 464

Text #2

Max Range: 7.7198. Min Range: -7.7198

Max Act: 7.7198. Min Act: -0.0000

Data Index: 1535208 (Python Code)

Max Activating Token Index: 396

Text #3

Max Range: 7.7198. Min Range: -7.7198

Max Act: 7.5109. Min Act: -0.0000

Data Index: 253540 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.7074. Min Act: -0.0000

Data Index: 1117278 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.5594. Min Act: -0.0000

Data Index: 1171602 (C4 (Web Text))

Max Activating Token Index: 736

Text #6

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.1126. Min Act: -0.0000

Data Index: 156725 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.6271. Min Act: -0.0000

Data Index: 983379 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.2071. Min Act: -0.0000

Data Index: 822016 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.8871. Min Act: -0.0000

Data Index: 375874 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.2759. Min Act: -0.0000

Data Index: 1124588 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.0746. Min Act: -0.0000

Data Index: 1121514 (C4 (Web Text))

Max Activating Token Index: 978

Text #12

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.0629. Min Act: -0.0000

Data Index: 511239 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.0504. Min Act: -0.0000

Data Index: 147697 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.1783. Min Act: -0.0000

Data Index: 450051 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.1444. Min Act: -0.0000

Data Index: 316856 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 7.7198. Min Range: -7.7198

Max Act: 5.9317. Min Act: -0.0000

Data Index: 401905 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 7.7198. Min Range: -7.7198

Max Act: 5.9156. Min Act: -0.0000

Data Index: 785128 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 7.7198. Min Range: -7.7198

Max Act: 5.6541. Min Act: -0.0000

Data Index: 528243 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 7.7198. Min Range: -7.7198

Max Act: 6.2501. Min Act: -0.0000

Data Index: 399083 (C4 (Web Text))

Max Activating Token Index: 470