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

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

Neuron 967 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: 0.0525. Min Range: -0.0525

Max Act: 0.0525. Min Act: -0.0002

Data Index: 328958 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0514. Min Act: -0.0002

Data Index: 921126 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0507. Min Act: -0.0002

Data Index: 737776 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0500. Min Act: -0.0002

Data Index: 1266594 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0439. Min Act: -0.0002

Data Index: 306691 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1242523 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0403. Min Act: -0.0002

Data Index: 837829 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0424. Min Act: -0.0002

Data Index: 1272385 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0421. Min Act: -0.0002

Data Index: 304232 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0420. Min Act: -0.0002

Data Index: 136331 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0409. Min Act: -0.0002

Data Index: 289227 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0439. Min Act: -0.0002

Data Index: 1171525 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0424. Min Act: -0.0002

Data Index: 921170 (C4 (Web Text))

Max Activating Token Index: 885

Text #13

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1192023 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0417. Min Act: -0.0002

Data Index: 571768 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1195552 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0409. Min Act: -0.0002

Data Index: 392705 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0398. Min Act: -0.0002

Data Index: 919535 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0410. Min Act: -0.0002

Data Index: 728538 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 0.0525. Min Range: -0.0525

Max Act: 0.0403. Min Act: -0.0002

Data Index: 553526 (C4 (Web Text))

Max Activating Token Index: 441