Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1410 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.6438. Min Act: -0.0001

Data Index: 450554 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1196508 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5715. Min Act: -0.0001

Data Index: 938531 (C4 (Web Text))

Max Activating Token Index: 508

Text #3

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5355. Min Act: -0.0001

Data Index: 192488 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.6191. Min Act: -0.0001

Data Index: 108801 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5628. Min Act: -0.0001

Data Index: 675133 (C4 (Web Text))

Max Activating Token Index: 445

Text #6

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5534. Min Act: -0.0001

Data Index: 587931 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5662. Min Act: -0.0001

Data Index: 933746 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1176043 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5448. Min Act: -0.0001

Data Index: 268136 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5756. Min Act: -0.0001

Data Index: 340433 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5363. Min Act: -0.0001

Data Index: 1337319 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5182. Min Act: -0.0001

Data Index: 46141 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5107. Min Act: -0.0001

Data Index: 82327 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5452. Min Act: -0.0001

Data Index: 1225839 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.6112. Min Act: -0.0001

Data Index: 1012004 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5401. Min Act: -0.0001

Data Index: 541161 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5321. Min Act: -0.0001

Data Index: 930319 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5619. Min Act: -0.0001

Data Index: 273436 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.6438. Min Range: -0.6438

Max Act: 0.5765. Min Act: -0.0001

Data Index: 139872 (C4 (Web Text))

Max Activating Token Index: 755