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

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

Neuron 2233 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0522. Min Act: -0.0004

Data Index: 609713 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0535. Min Act: -0.0004

Data Index: 835742 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0531. Min Act: -0.0004

Data Index: 618143 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0534. Min Act: -0.0004

Data Index: 787143 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0506. Min Act: -0.0004

Data Index: 991902 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0522. Min Act: -0.0004

Data Index: 1190122 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0518. Min Act: -0.0004

Data Index: 1119122 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0531. Min Act: -0.0004

Data Index: 20348 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0511. Min Act: -0.0004

Data Index: 271050 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0546. Min Act: -0.0004

Data Index: 186815 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0453. Min Act: -0.0004

Data Index: 552161 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0455. Min Act: -0.0004

Data Index: 536738 (C4 (Web Text))

Max Activating Token Index: 934

Text #12

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0520. Min Act: -0.0004

Data Index: 741192 (C4 (Web Text))

Max Activating Token Index: 562

Text #13

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0457. Min Act: -0.0004

Data Index: 62839 (C4 (Web Text))

Max Activating Token Index: 173

Text #14

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0464. Min Act: -0.0004

Data Index: 405736 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0403. Min Act: -0.0004

Data Index: 578641 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0471. Min Act: -0.0004

Data Index: 1191155 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0432. Min Act: -0.0004

Data Index: 886925 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0428. Min Act: -0.0004

Data Index: 920585 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0546. Min Range: -0.0546

Max Act: 0.0354. Min Act: -0.0004

Data Index: 325340 (C4 (Web Text))

Max Activating Token Index: 605