Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 310 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0003

Data Index: 933335 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0438. Min Act: -0.0003

Data Index: 651182 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0448. Min Act: -0.0003

Data Index: 740558 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0446. Min Act: -0.0003

Data Index: 726099 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0399. Min Act: -0.0003

Data Index: 1022409 (C4 (Web Text))

Max Activating Token Index: 342

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1155515 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0426. Min Act: -0.0003

Data Index: 279201 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0422. Min Act: -0.0003

Data Index: 1146805 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0403. Min Act: -0.0003

Data Index: 35882 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0412. Min Act: -0.0003

Data Index: 1271666 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0400. Min Act: -0.0003

Data Index: 100977 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0399. Min Act: -0.0002

Data Index: 24416 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0404. Min Act: -0.0002

Data Index: 226957 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0398. Min Act: -0.0003

Data Index: 610844 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0407. Min Act: -0.0002

Data Index: 20213 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1068760 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1354814 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0396. Min Act: -0.0003

Data Index: 913564 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0390. Min Act: -0.0003

Data Index: 30983 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0388. Min Act: -0.0002

Data Index: 119396 (C4 (Web Text))

Max Activating Token Index: 75