Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 742 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1093892 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1091313 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0533. Min Act: -0.0002

Data Index: 859197 (C4 (Web Text))

Max Activating Token Index: 551

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0506. Min Act: -0.0001

Data Index: 379585 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0507. Min Act: -0.0002

Data Index: 990670 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1132272 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0518. Min Act: -0.0002

Data Index: 783827 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0517. Min Act: -0.0002

Data Index: 961315 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1339766 (C4 (Web Text))

Max Activating Token Index: 976

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0494. Min Act: -0.0002

Data Index: 981457 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1240975 (C4 (Web Text))

Max Activating Token Index: 351

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0486. Min Act: -0.0002

Data Index: 869561 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0482. Min Act: -0.0002

Data Index: 198264 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0481. Min Act: -0.0002

Data Index: 454419 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0484. Min Act: -0.0002

Data Index: 853145 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0474. Min Act: -0.0002

Data Index: 554935 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1325564 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0468. Min Act: -0.0002

Data Index: 189314 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0473. Min Act: -0.0002

Data Index: 330857 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0467. Min Act: -0.0002

Data Index: 288580 (C4 (Web Text))

Max Activating Token Index: 262