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

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

Neuron 2455 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: 0.0658. Min Range: -0.0658

Max Act: 0.0658. Min Act: -0.0000

Data Index: 407819 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0622. Min Act: -0.0000

Data Index: 946814 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0608. Min Act: -0.0000

Data Index: 296920 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0591. Min Act: -0.0000

Data Index: 547389 (C4 (Web Text))

Max Activating Token Index: 873

Text #4

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0564. Min Act: -0.0000

Data Index: 546383 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0573. Min Act: -0.0000

Data Index: 741746 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0558. Min Act: -0.0000

Data Index: 994300 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0569. Min Act: -0.0000

Data Index: 409216 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0548. Min Act: -0.0000

Data Index: 463288 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0522. Min Act: -0.0000

Data Index: 535069 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0511. Min Act: -0.0000

Data Index: 516921 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0495. Min Act: -0.0000

Data Index: 990486 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1577723 (Python Code)

Max Activating Token Index: 974

Text #13

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0498. Min Act: -0.0000

Data Index: 395102 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0529. Min Act: -0.0000

Data Index: 396137 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1461131 (Python Code)

Max Activating Token Index: 656

Text #16

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0471. Min Act: -0.0000

Data Index: 637471 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0480. Min Act: -0.0000

Data Index: 1386169 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0488. Min Act: -0.0000

Data Index: 1003942 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0658. Min Range: -0.0658

Max Act: 0.0510. Min Act: -0.0000

Data Index: 767787 (C4 (Web Text))

Max Activating Token Index: 551