Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5026 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9946. Min Act: -0.0000

Data Index: 996434 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 2.0839. Min Range: -2.0839

Max Act: 2.0739. Min Act: -0.0000

Data Index: 1001116 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 2.0839. Min Range: -2.0839

Max Act: 2.0388. Min Act: -0.0000

Data Index: 107865 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 2.0839. Min Range: -2.0839

Max Act: 2.0839. Min Act: -0.0000

Data Index: 1280287 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.8721. Min Act: -0.0000

Data Index: 1170757 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9400. Min Act: -0.0000

Data Index: 730036 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1257260 (C4 (Web Text))

Max Activating Token Index: 274

Text #7

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9606. Min Act: -0.0000

Data Index: 1155362 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7379. Min Act: -0.0000

Data Index: 523917 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.8452. Min Act: -0.0000

Data Index: 796085 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.8351. Min Act: -0.0000

Data Index: 303856 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.9334. Min Act: -0.0000

Data Index: 6993 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6552. Min Act: -0.0000

Data Index: 1094147 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6503. Min Act: -0.0000

Data Index: 368287 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6856. Min Act: -0.0000

Data Index: 476851 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.7878. Min Act: -0.0000

Data Index: 16962 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6623. Min Act: -0.0000

Data Index: 99336 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.6539. Min Act: -0.0000

Data Index: 342381 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.3279. Min Act: -0.0000

Data Index: 363472 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 2.0839. Min Range: -2.0839

Max Act: 1.5900. Min Act: -0.0000

Data Index: 120184 (C4 (Web Text))

Max Activating Token Index: 144