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

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

Neuron 3999 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6246. Min Act: -0.0000

Data Index: 65592 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1392110 (Python Code)

Max Activating Token Index: 291

Text #2

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5076. Min Act: -0.0000

Data Index: 400964 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1538860 (Python Code)

Max Activating Token Index: 534

Text #4

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4538. Min Act: -0.0000

Data Index: 196427 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4413. Min Act: -0.0000

Data Index: 1463485 (Python Code)

Max Activating Token Index: 1005

Text #6

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1485662 (Python Code)

Max Activating Token Index: 126

Text #7

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3958. Min Act: -0.0000

Data Index: 875488 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1230207 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4134. Min Act: -0.0000

Data Index: 1631418 (Python Code)

Max Activating Token Index: 558

Text #10

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1272689 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1612916 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3836. Min Act: -0.0000

Data Index: 583977 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3650. Min Act: -0.0000

Data Index: 928253 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3618. Min Act: -0.0000

Data Index: 481179 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3841. Min Act: -0.0000

Data Index: 586956 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3801. Min Act: -0.0000

Data Index: 700996 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1127191 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1099943 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.3190. Min Act: -0.0000

Data Index: 787986 (C4 (Web Text))

Max Activating Token Index: 606