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

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

Neuron 3054 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.7754. Min Act: -0.0000

Data Index: 170118 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.7087. Min Act: -0.0000

Data Index: 631174 (C4 (Web Text))

Max Activating Token Index: 407

Text #2

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.6778. Min Act: -0.0000

Data Index: 287263 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.6134. Min Act: 0.0000

Data Index: 412269 (C4 (Web Text))

Max Activating Token Index: 77

Text #4

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5730. Min Act: 0.0000

Data Index: 208422 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5745. Min Act: 0.0000

Data Index: 992256 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5623. Min Act: -0.0000

Data Index: 128739 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5423. Min Act: 0.0001

Data Index: 350339 (C4 (Web Text))

Max Activating Token Index: 127

Text #8

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5327. Min Act: 0.0000

Data Index: 4273 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5448. Min Act: 0.0000

Data Index: 45732 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5297. Min Act: -0.0000

Data Index: 889301 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5484. Min Act: -0.0000

Data Index: 313774 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1032864 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1259920 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.4900. Min Act: 0.0000

Data Index: 295898 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.4900. Min Act: -0.0000

Data Index: 40470 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.4675. Min Act: 0.0000

Data Index: 1004225 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.4942. Min Act: 0.0000

Data Index: 472100 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.4836. Min Act: 0.0000

Data Index: 1105383 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 0.7754. Min Range: -0.7754

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1061043 (C4 (Web Text))

Max Activating Token Index: 910