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

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

Neuron 5650 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2310. Min Act: -0.0001

Data Index: 538178 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2450. Min Act: -0.0001

Data Index: 33753 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2659. Min Act: -0.0001

Data Index: 818214 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2508. Min Act: -0.0001

Data Index: 143872 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2276. Min Act: -0.0001

Data Index: 665462 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2137. Min Act: -0.0001

Data Index: 623474 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2195. Min Act: -0.0001

Data Index: 1110779 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2193. Min Act: -0.0001

Data Index: 158334 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2100. Min Act: -0.0001

Data Index: 1318632 (C4 (Web Text))

Max Activating Token Index: 458

Text #9

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2108. Min Act: -0.0001

Data Index: 574817 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.2114. Min Act: -0.0001

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1872. Min Act: -0.0001

Data Index: 503734 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1982. Min Act: -0.0001

Data Index: 462979 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1871. Min Act: -0.0001

Data Index: 919621 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1718. Min Act: -0.0001

Data Index: 223967 (C4 (Web Text))

Max Activating Token Index: 583

Text #15

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1761. Min Act: -0.0001

Data Index: 256252 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1654. Min Act: -0.0001

Data Index: 863618 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1711. Min Act: -0.0001

Data Index: 382747 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.2659. Min Range: -0.2659

Max Act: 0.1716. Min Act: -0.0001

Data Index: 612491 (C4 (Web Text))

Max Activating Token Index: 782