Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1573 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0557. Min Act: -0.0003

Data Index: 116322 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1157163 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0543. Min Act: -0.0003

Data Index: 835694 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0494. Min Act: -0.0003

Data Index: 455936 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0534. Min Act: -0.0003

Data Index: 872614 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0573. Min Act: -0.0003

Data Index: 948330 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0527. Min Act: -0.0003

Data Index: 748594 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0527. Min Act: -0.0003

Data Index: 849594 (C4 (Web Text))

Max Activating Token Index: 593

Text #8

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0508. Min Act: -0.0003

Data Index: 829923 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0509. Min Act: -0.0003

Data Index: 444521 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0506. Min Act: -0.0003

Data Index: 213125 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0502. Min Act: -0.0003

Data Index: 678565 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0484. Min Act: -0.0003

Data Index: 1162987 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0516. Min Act: -0.0003

Data Index: 249592 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0494. Min Act: -0.0003

Data Index: 431223 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0525. Min Act: -0.0003

Data Index: 467342 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0456. Min Act: -0.0003

Data Index: 625965 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1097129 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0525. Min Act: -0.0003

Data Index: 346702 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0573. Min Range: -0.0573

Max Act: 0.0475. Min Act: -0.0003

Data Index: 213493 (C4 (Web Text))

Max Activating Token Index: 112