Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4808 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5267. Min Act: -0.0001

Data Index: 293830 (C4 (Web Text))

Max Activating Token Index: 175

Text #1

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4164. Min Act: -0.0001

Data Index: 106397 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4860. Min Act: -0.0001

Data Index: 791012 (C4 (Web Text))

Max Activating Token Index: 62

Text #3

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4749. Min Act: -0.0001

Data Index: 1299376 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5346. Min Act: -0.0001

Data Index: 1183034 (C4 (Web Text))

Max Activating Token Index: 307

Text #5

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.5682. Min Act: -0.0001

Data Index: 481009 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1789. Min Act: -0.0001

Data Index: 416813 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.3736. Min Act: -0.0001

Data Index: 489424 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2817. Min Act: -0.0001

Data Index: 907025 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4043. Min Act: -0.0001

Data Index: 1093389 (C4 (Web Text))

Max Activating Token Index: 684

Text #10

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4648. Min Act: -0.0001

Data Index: 1181052 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1943. Min Act: -0.0001

Data Index: 240137 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.4721. Min Act: -0.0001

Data Index: 585915 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0801. Min Act: -0.0001

Data Index: 593905 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2371. Min Act: -0.0001

Data Index: 402515 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2082. Min Act: -0.0001

Data Index: 841698 (C4 (Web Text))

Max Activating Token Index: 327

Text #16

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1624. Min Act: -0.0001

Data Index: 22592 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.2261. Min Act: -0.0001

Data Index: 1235758 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.1343. Min Act: -0.0001

Data Index: 160695 (C4 (Web Text))

Max Activating Token Index: 91

Text #19

Max Range: 1.5682. Min Range: -1.5682

Max Act: 1.0949. Min Act: -0.0001

Data Index: 322282 (C4 (Web Text))

Max Activating Token Index: 633