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

Dataset: The Pile

Neuron 2538 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: 0.4714. Min Range: -0.4714

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1096415 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4550. Min Act: -0.0000

Data Index: 1865024 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4181. Min Act: -0.0000

Data Index: 590838 (The Pile)

Max Activating Token Index: 508

Text #3

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4552. Min Act: -0.0000

Data Index: 1108460 (The Pile)

Max Activating Token Index: 148

Text #4

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1961233 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1945704 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4221. Min Act: -0.0000

Data Index: 1679059 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1718465 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4248. Min Act: -0.0000

Data Index: 916223 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4217. Min Act: -0.0000

Data Index: 1374734 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4094. Min Act: -0.0000

Data Index: 175292 (The Pile)

Max Activating Token Index: 295

Text #11

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4044. Min Act: -0.0000

Data Index: 352281 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3956. Min Act: -0.0000

Data Index: 380656 (The Pile)

Max Activating Token Index: 681

Text #13

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1300540 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3732. Min Act: -0.0000

Data Index: 156662 (The Pile)

Max Activating Token Index: 284

Text #15

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3731. Min Act: -0.0000

Data Index: 358063 (The Pile)

Max Activating Token Index: 238

Text #16

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3653. Min Act: -0.0000

Data Index: 201717 (The Pile)

Max Activating Token Index: 233

Text #17

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3535. Min Act: -0.0000

Data Index: 793120 (The Pile)

Max Activating Token Index: 100

Text #18

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4047. Min Act: -0.0000

Data Index: 1423820 (The Pile)

Max Activating Token Index: 958

Text #19

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3622. Min Act: -0.0000

Data Index: 1405426 (The Pile)

Max Activating Token Index: 782