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

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

Neuron 618 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: 6.5493. Min Range: -6.5493

Max Act: 6.5493. Min Act: -0.0000

Data Index: 934539 (C4 (Web Text))

Max Activating Token Index: 264

Text #1

Max Range: 6.5493. Min Range: -6.5493

Max Act: 5.4148. Min Act: -0.0000

Data Index: 703379 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.8137. Min Act: -0.0000

Data Index: 358270 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.8836. Min Act: -0.0000

Data Index: 458786 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.7941. Min Act: -0.0000

Data Index: 403589 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.3680. Min Act: -0.0000

Data Index: 561850 (C4 (Web Text))

Max Activating Token Index: 539

Text #6

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.3277. Min Act: -0.0000

Data Index: 653645 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.5145. Min Act: -0.0000

Data Index: 327053 (C4 (Web Text))

Max Activating Token Index: 394

Text #8

Max Range: 6.5493. Min Range: -6.5493

Max Act: 3.9071. Min Act: -0.0000

Data Index: 118618 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.2531. Min Act: -0.0000

Data Index: 999695 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.3774. Min Act: -0.0000

Data Index: 556395 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.3578. Min Act: -0.0000

Data Index: 1066387 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 6.5493. Min Range: -6.5493

Max Act: 3.9526. Min Act: -0.0000

Data Index: 1087749 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.2226. Min Act: -0.0000

Data Index: 483366 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.0512. Min Act: -0.0000

Data Index: 810206 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.1880. Min Act: -0.0000

Data Index: 1053022 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.1733. Min Act: -0.0000

Data Index: 1193422 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.1575. Min Act: -0.0000

Data Index: 570197 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 6.5493. Min Range: -6.5493

Max Act: 4.1908. Min Act: -0.0000

Data Index: 48149 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 6.5493. Min Range: -6.5493

Max Act: 3.4882. Min Act: -0.0000

Data Index: 1326490 (C4 (Web Text))

Max Activating Token Index: 539