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

Dataset: The Pile

Neuron 952 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: 1.5640. Min Range: -1.5640

Max Act: 1.5332. Min Act: -0.0000

Data Index: 373040 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4693. Min Act: -0.0000

Data Index: 1808446 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4011. Min Act: -0.0000

Data Index: 494619 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.5640. Min Act: -0.0000

Data Index: 244323 (The Pile)

Max Activating Token Index: 752

Text #4

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3157. Min Act: -0.0000

Data Index: 1718585 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3864. Min Act: -0.0000

Data Index: 1615526 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3004. Min Act: -0.0000

Data Index: 625987 (The Pile)

Max Activating Token Index: 317

Text #7

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4442. Min Act: -0.0000

Data Index: 237792 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4487. Min Act: -0.0000

Data Index: 1282388 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2056. Min Act: -0.0000

Data Index: 104566 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1616331 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2271. Min Act: -0.0000

Data Index: 1367245 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2777. Min Act: -0.0000

Data Index: 1543201 (The Pile)

Max Activating Token Index: 224

Text #13

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3651. Min Act: -0.0000

Data Index: 585808 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1815695 (The Pile)

Max Activating Token Index: 508

Text #15

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3149. Min Act: -0.0000

Data Index: 489199 (The Pile)

Max Activating Token Index: 264

Text #16

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3085. Min Act: -0.0000

Data Index: 153061 (The Pile)

Max Activating Token Index: 451

Text #17

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3430. Min Act: -0.0000

Data Index: 964580 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1465321 (The Pile)

Max Activating Token Index: 686

Text #19

Max Range: 1.5640. Min Range: -1.5640

Max Act: 1.2632. Min Act: -0.0000

Data Index: 260089 (The Pile)

Max Activating Token Index: 81