Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 602 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2625. Min Act: -0.0003

Data Index: 957295 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.2088. Min Act: -0.0003

Data Index: 96611 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1978. Min Act: -0.0003

Data Index: 1096272 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1824. Min Act: -0.0003

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1693. Min Act: -0.0003

Data Index: 486021 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1622. Min Act: -0.0003

Data Index: 330938 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1715. Min Act: -0.0003

Data Index: 1575383 (Python Code)

Max Activating Token Index: 868

Text #7

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1501. Min Act: -0.0003

Data Index: 461486 (C4 (Web Text))

Max Activating Token Index: 323

Text #8

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1549. Min Act: -0.0003

Data Index: 1103797 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1514. Min Act: -0.0003

Data Index: 929002 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1493. Min Act: -0.0003

Data Index: 144450 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1476. Min Act: -0.0003

Data Index: 1243471 (C4 (Web Text))

Max Activating Token Index: 625

Text #12

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1432. Min Act: -0.0003

Data Index: 838430 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1340. Min Act: -0.0003

Data Index: 1386557 (Python Code)

Max Activating Token Index: 514

Text #14

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1426. Min Act: -0.0003

Data Index: 854194 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1273. Min Act: -0.0003

Data Index: 955248 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1341. Min Act: -0.0003

Data Index: 827697 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1322. Min Act: -0.0003

Data Index: 953459 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1301. Min Act: -0.0003

Data Index: 890734 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 0.2625. Min Range: -0.2625

Max Act: 0.1223. Min Act: -0.0003

Data Index: 360615 (C4 (Web Text))

Max Activating Token Index: 406