Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2606 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1784. Min Act: -0.0001

Data Index: 593244 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1739. Min Act: -0.0001

Data Index: 1285281 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1807. Min Act: -0.0001

Data Index: 49653 (C4 (Web Text))

Max Activating Token Index: 112

Text #3

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1783. Min Act: -0.0001

Data Index: 835175 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1813. Min Act: -0.0001

Data Index: 976669 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1733. Min Act: -0.0001

Data Index: 669611 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1151382 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1018181 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1682. Min Act: -0.0001

Data Index: 664297 (C4 (Web Text))

Max Activating Token Index: 643

Text #9

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1694. Min Act: -0.0001

Data Index: 957260 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1682. Min Act: -0.0001

Data Index: 327388 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1683. Min Act: -0.0001

Data Index: 482520 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1116891 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1661. Min Act: -0.0001

Data Index: 521134 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1662. Min Act: -0.0001

Data Index: 996352 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1705. Min Act: -0.0001

Data Index: 1063893 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1636. Min Act: -0.0001

Data Index: 10587 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1231439 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1565. Min Act: -0.0001

Data Index: 459391 (C4 (Web Text))

Max Activating Token Index: 544

Text #19

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1626. Min Act: -0.0001

Data Index: 372266 (C4 (Web Text))

Max Activating Token Index: 209