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

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

Neuron 2701 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3464. Min Act: -0.0000

Data Index: 526027 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3531. Min Act: -0.0000

Data Index: 435063 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.3568. Min Act: -0.0000

Data Index: 1299035 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2777. Min Act: -0.0000

Data Index: 448174 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2810. Min Act: -0.0000

Data Index: 173069 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2399. Min Act: -0.0000

Data Index: 398993 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2560. Min Act: -0.0000

Data Index: 708866 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2296. Min Act: -0.0000

Data Index: 468596 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1097611 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2537. Min Act: -0.0000

Data Index: 460255 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1345265 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2429. Min Act: -0.0000

Data Index: 328357 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2108. Min Act: -0.0000

Data Index: 495140 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2125. Min Act: -0.0000

Data Index: 304585 (C4 (Web Text))

Max Activating Token Index: 660

Text #14

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2115. Min Act: -0.0000

Data Index: 200557 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.2097. Min Act: -0.0000

Data Index: 735743 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.1952. Min Act: -0.0000

Data Index: 228321 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.1943. Min Act: -0.0000

Data Index: 1246482 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.1988. Min Act: -0.0000

Data Index: 1054763 (C4 (Web Text))

Max Activating Token Index: 638

Text #19

Max Range: 0.3568. Min Range: -0.3568

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1065712 (C4 (Web Text))

Max Activating Token Index: 894