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

Dataset: The Pile

Neuron 4833 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: 1.6677. Min Range: -1.6677

Max Act: 1.5745. Min Act: -0.0000

Data Index: 1511229 (The Pile)

Max Activating Token Index: 640

Text #1

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.5390. Min Act: -0.0000

Data Index: 907511 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3855. Min Act: -0.0000

Data Index: 492439 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.5280. Min Act: -0.0000

Data Index: 1859319 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4154. Min Act: -0.0000

Data Index: 603967 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.6677. Min Act: -0.0000

Data Index: 561480 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4662. Min Act: -0.0000

Data Index: 857921 (The Pile)

Max Activating Token Index: 948

Text #7

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1307641 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4382. Min Act: -0.0000

Data Index: 1583751 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4850. Min Act: -0.0000

Data Index: 449556 (The Pile)

Max Activating Token Index: 565

Text #10

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3259. Min Act: -0.0000

Data Index: 412821 (The Pile)

Max Activating Token Index: 529

Text #11

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3914. Min Act: -0.0000

Data Index: 1497955 (The Pile)

Max Activating Token Index: 242

Text #12

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4557. Min Act: -0.0000

Data Index: 710888 (The Pile)

Max Activating Token Index: 87

Text #13

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3772. Min Act: -0.0000

Data Index: 1575361 (The Pile)

Max Activating Token Index: 448

Text #14

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.2552. Min Act: -0.0000

Data Index: 1240376 (The Pile)

Max Activating Token Index: 153

Text #15

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3441. Min Act: -0.0000

Data Index: 1585609 (The Pile)

Max Activating Token Index: 71

Text #16

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.4347. Min Act: -0.0000

Data Index: 180039 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3346. Min Act: -0.0000

Data Index: 605373 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1156500 (The Pile)

Max Activating Token Index: 260

Text #19

Max Range: 1.6677. Min Range: -1.6677

Max Act: 1.2682. Min Act: -0.0000

Data Index: 597756 (The Pile)

Max Activating Token Index: 586