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

Dataset: The Pile

Neuron 3218 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.3682. Min Act: -0.0000

Data Index: 584951 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.3295. Min Act: -0.0000

Data Index: 1452521 (The Pile)

Max Activating Token Index: 221

Text #2

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2349. Min Act: -0.0000

Data Index: 1436167 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.3552. Min Act: -0.0000

Data Index: 887066 (The Pile)

Max Activating Token Index: 560

Text #4

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2033. Min Act: -0.0000

Data Index: 584470 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.2778. Min Act: -0.0000

Data Index: 302593 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1577. Min Act: -0.0000

Data Index: 1765479 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1214107 (The Pile)

Max Activating Token Index: 467

Text #8

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1467. Min Act: -0.0000

Data Index: 166888 (The Pile)

Max Activating Token Index: 448

Text #9

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1410. Min Act: -0.0000

Data Index: 975194 (The Pile)

Max Activating Token Index: 852

Text #10

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1271. Min Act: -0.0000

Data Index: 416887 (The Pile)

Max Activating Token Index: 671

Text #11

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1147. Min Act: -0.0000

Data Index: 1207614 (The Pile)

Max Activating Token Index: 722

Text #12

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0601. Min Act: -0.0000

Data Index: 754528 (The Pile)

Max Activating Token Index: 696

Text #13

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.1824. Min Act: -0.0000

Data Index: 539140 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0955. Min Act: -0.0000

Data Index: 619895 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1820866 (The Pile)

Max Activating Token Index: 184

Text #16

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0696. Min Act: -0.0000

Data Index: 406123 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0733. Min Act: -0.0000

Data Index: 718727 (The Pile)

Max Activating Token Index: 833

Text #18

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0673. Min Act: -0.0000

Data Index: 334609 (The Pile)

Max Activating Token Index: 347

Text #19

Max Range: 1.3682. Min Range: -1.3682

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1792869 (The Pile)

Max Activating Token Index: 332