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

Dataset: The Pile

Neuron 2642 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1295451 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1202246 (The Pile)

Max Activating Token Index: 75

Text #2

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1562326 (The Pile)

Max Activating Token Index: 212

Text #3

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4533. Min Act: -0.0000

Data Index: 48703 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4950. Min Act: -0.0000

Data Index: 1372214 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1306414 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1446439 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4487. Min Act: -0.0000

Data Index: 157262 (The Pile)

Max Activating Token Index: 540

Text #8

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1780209 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4379. Min Act: -0.0000

Data Index: 889300 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1768049 (The Pile)

Max Activating Token Index: 130

Text #11

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1046664 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4680. Min Act: -0.0000

Data Index: 223567 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1516566 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1115997 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4232. Min Act: -0.0000

Data Index: 777363 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4205. Min Act: -0.0000

Data Index: 82864 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4597. Min Act: -0.0000

Data Index: 1502328 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4298. Min Act: -0.0000

Data Index: 981705 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1010030 (The Pile)

Max Activating Token Index: 401