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

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

Neuron 4929 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1377. Min Range: -4.1377

Max Act: 4.1377. Min Act: -0.0000

Data Index: 1128442 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.5412. Min Act: -0.0000

Data Index: 1207312 (C4 (Web Text))

Max Activating Token Index: 201

Text #2

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.5757. Min Act: -0.0000

Data Index: 1258741 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.1912. Min Act: -0.0000

Data Index: 1182330 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.1607. Min Act: -0.0000

Data Index: 507477 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.9840. Min Act: -0.0000

Data Index: 165957 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.0741. Min Act: -0.0000

Data Index: 1175371 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.0687. Min Act: -0.0000

Data Index: 61989 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.2044. Min Act: -0.0000

Data Index: 596488 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 4.1377. Min Range: -4.1377

Max Act: 3.0469. Min Act: -0.0000

Data Index: 689162 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.9803. Min Act: -0.0000

Data Index: 1052556 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.9005. Min Act: -0.0000

Data Index: 514490 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.7349. Min Act: -0.0000

Data Index: 791771 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.9475. Min Act: -0.0000

Data Index: 1040182 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.6120. Min Act: -0.0000

Data Index: 261476 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.7127. Min Act: -0.0000

Data Index: 626294 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.9258. Min Act: -0.0000

Data Index: 816274 (C4 (Web Text))

Max Activating Token Index: 773

Text #17

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.3954. Min Act: -0.0000

Data Index: 734943 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.5721. Min Act: -0.0000

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 4.1377. Min Range: -4.1377

Max Act: 2.4242. Min Act: -0.0000

Data Index: 1051981 (C4 (Web Text))

Max Activating Token Index: 748