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

Dataset: The Pile

Neuron 1209 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: 3.4291. Min Range: -3.4291

Max Act: 3.4291. Min Act: -0.0000

Data Index: 1070959 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 3.4291. Min Range: -3.4291

Max Act: 3.2862. Min Act: -0.0000

Data Index: 1330467 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 3.4291. Min Range: -3.4291

Max Act: 3.1907. Min Act: -0.0000

Data Index: 498974 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 3.4291. Min Range: -3.4291

Max Act: 3.2182. Min Act: -0.0000

Data Index: 1090336 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.7891. Min Act: -0.0000

Data Index: 1736910 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.7825. Min Act: -0.0000

Data Index: 1236315 (The Pile)

Max Activating Token Index: 289

Text #6

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.6179. Min Act: -0.0000

Data Index: 1995007 (The Pile)

Max Activating Token Index: 50

Text #7

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.4404. Min Act: -0.0000

Data Index: 1712418 (The Pile)

Max Activating Token Index: 110

Text #8

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.5265. Min Act: -0.0000

Data Index: 343032 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.5426. Min Act: -0.0000

Data Index: 1446943 (The Pile)

Max Activating Token Index: 611

Text #10

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.2948. Min Act: -0.0000

Data Index: 1454867 (The Pile)

Max Activating Token Index: 409

Text #11

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1428012 (The Pile)

Max Activating Token Index: 154

Text #12

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.4896. Min Act: -0.0000

Data Index: 34080 (The Pile)

Max Activating Token Index: 721

Text #13

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.3490. Min Act: -0.0000

Data Index: 557810 (The Pile)

Max Activating Token Index: 69

Text #14

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.2156. Min Act: -0.0000

Data Index: 1156188 (The Pile)

Max Activating Token Index: 465

Text #15

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.2998. Min Act: -0.0000

Data Index: 1431570 (The Pile)

Max Activating Token Index: 204

Text #16

Max Range: 3.4291. Min Range: -3.4291

Max Act: 1.9386. Min Act: -0.0000

Data Index: 1112509 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.1430. Min Act: -0.0000

Data Index: 522409 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.0431. Min Act: -0.0000

Data Index: 133329 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 3.4291. Min Range: -3.4291

Max Act: 2.1350. Min Act: -0.0000

Data Index: 1546297 (The Pile)

Max Activating Token Index: 437