Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1845 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.4712. Min Range: -3.4712

Max Act: 3.3903. Min Act: -0.0000

Data Index: 1532362 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 3.4712. Min Range: -3.4712

Max Act: 3.4712. Min Act: -0.0000

Data Index: 1949816 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.9087. Min Act: -0.0000

Data Index: 1302736 (The Pile)

Max Activating Token Index: 806

Text #3

Max Range: 3.4712. Min Range: -3.4712

Max Act: 3.1988. Min Act: -0.0000

Data Index: 1177940 (The Pile)

Max Activating Token Index: 430

Text #4

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.9437. Min Act: -0.0000

Data Index: 1383991 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 3.4712. Min Range: -3.4712

Max Act: 3.3487. Min Act: -0.0000

Data Index: 1376102 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.9628. Min Act: -0.0000

Data Index: 1601791 (The Pile)

Max Activating Token Index: 171

Text #7

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.8866. Min Act: -0.0000

Data Index: 35434 (The Pile)

Max Activating Token Index: 424

Text #8

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.8495. Min Act: -0.0000

Data Index: 1266268 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.9766. Min Act: -0.0000

Data Index: 1824172 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7812. Min Act: -0.0000

Data Index: 1473077 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7504. Min Act: -0.0000

Data Index: 659286 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7663. Min Act: -0.0000

Data Index: 804675 (The Pile)

Max Activating Token Index: 164

Text #13

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.8825. Min Act: -0.0000

Data Index: 927057 (The Pile)

Max Activating Token Index: 352

Text #14

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7277. Min Act: -0.0000

Data Index: 222435 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.5710. Min Act: -0.0000

Data Index: 1316230 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.5601. Min Act: -0.0000

Data Index: 1451892 (The Pile)

Max Activating Token Index: 516

Text #17

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.6231. Min Act: -0.0000

Data Index: 1048464 (The Pile)

Max Activating Token Index: 758

Text #18

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.6205. Min Act: -0.0000

Data Index: 1536579 (The Pile)

Max Activating Token Index: 267

Text #19

Max Range: 3.4712. Min Range: -3.4712

Max Act: 2.7776. Min Act: -0.0000

Data Index: 58919 (The Pile)

Max Activating Token Index: 504