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

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

Neuron 613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0632. Min Act: -0.0002

Data Index: 795815 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0473. Min Act: -0.0002

Data Index: 920911 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0475. Min Act: -0.0002

Data Index: 165757 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1132904 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1169665 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0446. Min Act: -0.0002

Data Index: 485404 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0418. Min Act: -0.0002

Data Index: 251373 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0432. Min Act: -0.0002

Data Index: 967463 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1336203 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0439. Min Act: -0.0002

Data Index: 667749 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1076929 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1255378 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0426. Min Act: -0.0002

Data Index: 118736 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1151220 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0423. Min Act: -0.0002

Data Index: 20773 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0420. Min Act: -0.0002

Data Index: 82251 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1169817 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0424. Min Act: -0.0002

Data Index: 601731 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0411. Min Act: -0.0002

Data Index: 108871 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0632. Min Range: -0.0632

Max Act: 0.0419. Min Act: -0.0002

Data Index: 101932 (C4 (Web Text))

Max Activating Token Index: 287