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

Dataset: The Pile

Neuron 4989 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1495293 (The Pile)

Max Activating Token Index: 552

Text #1

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.5242. Min Act: -0.0000

Data Index: 1471690 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4724. Min Act: -0.0000

Data Index: 738110 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1251627 (The Pile)

Max Activating Token Index: 831

Text #4

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4608. Min Act: -0.0000

Data Index: 391816 (The Pile)

Max Activating Token Index: 880

Text #5

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4351. Min Act: -0.0000

Data Index: 667185 (The Pile)

Max Activating Token Index: 652

Text #6

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4129. Min Act: -0.0000

Data Index: 526942 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4336. Min Act: -0.0000

Data Index: 1149699 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1216618 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3687. Min Act: -0.0000

Data Index: 703302 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4584. Min Act: -0.0000

Data Index: 1173029 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3512. Min Act: -0.0000

Data Index: 231473 (The Pile)

Max Activating Token Index: 729

Text #12

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1620667 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4183. Min Act: -0.0000

Data Index: 1536387 (The Pile)

Max Activating Token Index: 869

Text #14

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3946. Min Act: -0.0000

Data Index: 751284 (The Pile)

Max Activating Token Index: 580

Text #15

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1321238 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3712. Min Act: -0.0000

Data Index: 289296 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1189859 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1892908 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 0.5242. Min Range: -0.5242

Max Act: 0.3457. Min Act: -0.0000

Data Index: 420004 (The Pile)

Max Activating Token Index: 579