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

Dataset: The Pile

Neuron 2833 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.9161. Min Act: -0.0000

Data Index: 442913 (The Pile)

Max Activating Token Index: 958

Text #1

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.7276. Min Act: -0.0000

Data Index: 850642 (The Pile)

Max Activating Token Index: 278

Text #2

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.1212. Min Act: -0.0000

Data Index: 27705 (The Pile)

Max Activating Token Index: 666

Text #3

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.4172. Min Act: -0.0000

Data Index: 1359910 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.0109. Min Act: -0.0000

Data Index: 1444681 (The Pile)

Max Activating Token Index: 360

Text #5

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.2124. Min Act: -0.0000

Data Index: 1576173 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.3400. Min Act: -0.0000

Data Index: 1530618 (The Pile)

Max Activating Token Index: 208

Text #7

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.2805. Min Act: -0.0000

Data Index: 890682 (The Pile)

Max Activating Token Index: 215

Text #8

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.2884. Min Act: -0.0000

Data Index: 488873 (The Pile)

Max Activating Token Index: 820

Text #9

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.1940. Min Act: -0.0000

Data Index: 1169848 (The Pile)

Max Activating Token Index: 747

Text #10

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.1124. Min Act: -0.0000

Data Index: 1922352 (The Pile)

Max Activating Token Index: 620

Text #11

Max Range: 5.9161. Min Range: -5.9161

Max Act: 4.9595. Min Act: -0.0000

Data Index: 321870 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.0816. Min Act: -0.0000

Data Index: 71425 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.0514. Min Act: -0.0000

Data Index: 1127309 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 5.9161. Min Range: -5.9161

Max Act: 5.0303. Min Act: -0.0000

Data Index: 247129 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 5.9161. Min Range: -5.9161

Max Act: 4.8382. Min Act: -0.0000

Data Index: 1012501 (The Pile)

Max Activating Token Index: 782

Text #16

Max Range: 5.9161. Min Range: -5.9161

Max Act: 4.9292. Min Act: -0.0000

Data Index: 1838732 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 5.9161. Min Range: -5.9161

Max Act: 4.3470. Min Act: -0.0000

Data Index: 770491 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 5.9161. Min Range: -5.9161

Max Act: 4.7052. Min Act: -0.0000

Data Index: 985680 (The Pile)

Max Activating Token Index: 606

Text #19

Max Range: 5.9161. Min Range: -5.9161

Max Act: 4.6683. Min Act: -0.0000

Data Index: 1748140 (The Pile)

Max Activating Token Index: 319