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

Dataset: The Pile

Neuron 879 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.2497. Min Act: -0.0000

Data Index: 37726 (The Pile)

Max Activating Token Index: 67

Text #1

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1886082 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1517156 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 1.2497. Min Range: -1.2497

Max Act: 1.1540. Min Act: -0.0000

Data Index: 574425 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9988. Min Act: -0.0000

Data Index: 96139 (The Pile)

Max Activating Token Index: 152

Text #5

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9316. Min Act: -0.0000

Data Index: 1470701 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.8938. Min Act: -0.0000

Data Index: 1460683 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.9772. Min Act: -0.0000

Data Index: 511485 (The Pile)

Max Activating Token Index: 799

Text #8

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1754824 (The Pile)

Max Activating Token Index: 401

Text #9

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1957925 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.7377. Min Act: -0.0000

Data Index: 375661 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1167117 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1681164 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6443. Min Act: -0.0000

Data Index: 90243 (The Pile)

Max Activating Token Index: 10

Text #14

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6084. Min Act: -0.0000

Data Index: 1525812 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.6366. Min Act: -0.0000

Data Index: 832844 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1659029 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5879. Min Act: -0.0000

Data Index: 480350 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5860. Min Act: -0.0000

Data Index: 195231 (The Pile)

Max Activating Token Index: 840

Text #19

Max Range: 1.2497. Min Range: -1.2497

Max Act: 0.5516. Min Act: -0.0000

Data Index: 787322 (The Pile)

Max Activating Token Index: 200