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

Dataset: The Pile

Neuron 1833 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: 1.2763. Min Range: -1.2763

Max Act: 1.2763. Min Act: -0.0000

Data Index: 1166684 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 1.2763. Min Range: -1.2763

Max Act: 1.0456. Min Act: -0.0000

Data Index: 368690 (The Pile)

Max Activating Token Index: 992

Text #2

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1497432 (The Pile)

Max Activating Token Index: 478

Text #3

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8654. Min Act: -0.0000

Data Index: 230587 (The Pile)

Max Activating Token Index: 433

Text #4

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8998. Min Act: -0.0000

Data Index: 217901 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8471. Min Act: -0.0000

Data Index: 946150 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8634. Min Act: -0.0000

Data Index: 789664 (The Pile)

Max Activating Token Index: 514

Text #7

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1243455 (The Pile)

Max Activating Token Index: 707

Text #8

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8831. Min Act: -0.0000

Data Index: 860364 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1720424 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1253929 (The Pile)

Max Activating Token Index: 173

Text #11

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7682. Min Act: -0.0000

Data Index: 527122 (The Pile)

Max Activating Token Index: 485

Text #12

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7223. Min Act: -0.0000

Data Index: 752933 (The Pile)

Max Activating Token Index: 157

Text #13

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7131. Min Act: -0.0000

Data Index: 1457155 (The Pile)

Max Activating Token Index: 581

Text #14

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7117. Min Act: -0.0000

Data Index: 1418107 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.8019. Min Act: -0.0000

Data Index: 568595 (The Pile)

Max Activating Token Index: 881

Text #16

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1072534 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7224. Min Act: -0.0000

Data Index: 92630 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.6763. Min Act: -0.0000

Data Index: 646631 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 1.2763. Min Range: -1.2763

Max Act: 0.7109. Min Act: -0.0000

Data Index: 876724 (The Pile)

Max Activating Token Index: 51