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

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

Neuron 492 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.9637. Min Act: -0.0000

Data Index: 950048 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.2149. Min Act: -0.0000

Data Index: 1312148 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 2.9637. Min Range: -2.9637

Max Act: 2.0214. Min Act: -0.0000

Data Index: 1101661 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.9696. Min Act: -0.0000

Data Index: 1194513 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.9567. Min Act: -0.0000

Data Index: 714949 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.8423. Min Act: -0.0000

Data Index: 382517 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7457. Min Act: -0.0000

Data Index: 77486 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7955. Min Act: -0.0000

Data Index: 239833 (C4 (Web Text))

Max Activating Token Index: 818

Text #8

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7888. Min Act: -0.0000

Data Index: 632017 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.7223. Min Act: -0.0000

Data Index: 414246 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.6647. Min Act: -0.0000

Data Index: 952602 (C4 (Web Text))

Max Activating Token Index: 1015

Text #11

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.5570. Min Act: -0.0000

Data Index: 540080 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.6824. Min Act: -0.0000

Data Index: 1296836 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.5627. Min Act: -0.0000

Data Index: 471841 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.4744. Min Act: -0.0000

Data Index: 331067 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.5581. Min Act: -0.0000

Data Index: 423583 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.5478. Min Act: -0.0000

Data Index: 40933 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.5243. Min Act: -0.0000

Data Index: 993949 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.5197. Min Act: -0.0000

Data Index: 1201488 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 2.9637. Min Range: -2.9637

Max Act: 1.5068. Min Act: -0.0000

Data Index: 712689 (C4 (Web Text))

Max Activating Token Index: 528