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

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

Neuron 6001 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1714. Min Range: -5.1714

Max Act: 5.1714. Min Act: -0.0000

Data Index: 642141 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.7675. Min Act: -0.0000

Data Index: 933732 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 5.1714. Min Range: -5.1714

Max Act: 4.4805. Min Act: -0.0000

Data Index: 871285 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 5.1714. Min Range: -5.1714

Max Act: 3.7182. Min Act: -0.0000

Data Index: 338485 (C4 (Web Text))

Max Activating Token Index: 825

Text #4

Max Range: 5.1714. Min Range: -5.1714

Max Act: 3.7718. Min Act: -0.0000

Data Index: 1248823 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 5.1714. Min Range: -5.1714

Max Act: 3.5745. Min Act: -0.0000

Data Index: 351864 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 5.1714. Min Range: -5.1714

Max Act: 3.4871. Min Act: -0.0000

Data Index: 115554 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 5.1714. Min Range: -5.1714

Max Act: 3.0887. Min Act: -0.0000

Data Index: 440644 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 5.1714. Min Range: -5.1714

Max Act: 3.3886. Min Act: -0.0000

Data Index: 359268 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 5.1714. Min Range: -5.1714

Max Act: 3.1736. Min Act: -0.0000

Data Index: 492790 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.9551. Min Act: -0.0000

Data Index: 1282089 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.7235. Min Act: -0.0000

Data Index: 264887 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.5913. Min Act: -0.0000

Data Index: 360321 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.4771. Min Act: -0.0000

Data Index: 840200 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.4615. Min Act: -0.0000

Data Index: 1312017 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.0819. Min Act: -0.0000

Data Index: 761821 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.1839. Min Act: -0.0000

Data Index: 701937 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.2596. Min Act: -0.0000

Data Index: 88966 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.2244. Min Act: -0.0000

Data Index: 152240 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 5.1714. Min Range: -5.1714

Max Act: 2.2407. Min Act: -0.0000

Data Index: 314208 (C4 (Web Text))

Max Activating Token Index: 331