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

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

Neuron 5759 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: 1.4298. Min Range: -1.4298

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1355177 (C4 (Web Text))

Max Activating Token Index: 985

Text #1

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.3240. Min Act: -0.0000

Data Index: 712718 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.3697. Min Act: -0.0001

Data Index: 553682 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.2768. Min Act: -0.0000

Data Index: 557805 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.3797. Min Act: -0.0000

Data Index: 403117 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.2497. Min Act: -0.0000

Data Index: 920093 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.2068. Min Act: -0.0000

Data Index: 761287 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1289. Min Act: -0.0001

Data Index: 726283 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1558. Min Act: -0.0000

Data Index: 158345 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1733. Min Act: -0.0000

Data Index: 213802 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1134. Min Act: -0.0000

Data Index: 594270 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0712. Min Act: -0.0000

Data Index: 1280659 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1974. Min Act: -0.0000

Data Index: 220285 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0769. Min Act: -0.0000

Data Index: 639823 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0926. Min Act: -0.0001

Data Index: 429210 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1573. Min Act: -0.0000

Data Index: 873187 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.1689. Min Act: -0.0000

Data Index: 992128 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0516. Min Act: -0.0000

Data Index: 513163 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 1.4298. Min Range: -1.4298

Max Act: 0.9494. Min Act: -0.0000

Data Index: 236111 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.4298. Min Range: -1.4298

Max Act: 1.0782. Min Act: -0.0000

Data Index: 532103 (C4 (Web Text))

Max Activating Token Index: 543