Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 879 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1070346 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7789. Min Act: -0.0000

Data Index: 1066872 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7130. Min Act: -0.0000

Data Index: 96245 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1878278 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6761. Min Act: -0.0000

Data Index: 29153 (The Pile)

Max Activating Token Index: 969

Text #5

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7048. Min Act: -0.0000

Data Index: 1343867 (The Pile)

Max Activating Token Index: 279

Text #6

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1242122 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1095932 (The Pile)

Max Activating Token Index: 686

Text #8

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6788. Min Act: -0.0000

Data Index: 867277 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1154997 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6492. Min Act: -0.0000

Data Index: 78224 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6580. Min Act: -0.0000

Data Index: 1984352 (The Pile)

Max Activating Token Index: 191

Text #12

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6832. Min Act: -0.0000

Data Index: 869047 (The Pile)

Max Activating Token Index: 299

Text #13

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1973219 (The Pile)

Max Activating Token Index: 750

Text #14

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6245. Min Act: -0.0000

Data Index: 329594 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6522. Min Act: -0.0000

Data Index: 562363 (The Pile)

Max Activating Token Index: 1010

Text #16

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6446. Min Act: -0.0000

Data Index: 1289732 (The Pile)

Max Activating Token Index: 294

Text #17

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1282580 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6324. Min Act: -0.0000

Data Index: 783827 (The Pile)

Max Activating Token Index: 493

Text #19

Max Range: 0.8648. Min Range: -0.8648

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1582479 (The Pile)

Max Activating Token Index: 783