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

Dataset: The Pile

Neuron 2312 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: 0.5997. Min Range: -0.5997

Max Act: 0.5997. Min Act: -0.0000

Data Index: 554238 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5432. Min Act: -0.0000

Data Index: 334172 (The Pile)

Max Activating Token Index: 521

Text #2

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5554. Min Act: -0.0000

Data Index: 815032 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.5189. Min Act: 0.0000

Data Index: 1342480 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4964. Min Act: -0.0000

Data Index: 417852 (The Pile)

Max Activating Token Index: 996

Text #5

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4771. Min Act: -0.0000

Data Index: 1626232 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4870. Min Act: -0.0000

Data Index: 614765 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1807051 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4507. Min Act: -0.0000

Data Index: 433727 (The Pile)

Max Activating Token Index: 505

Text #9

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4552. Min Act: -0.0000

Data Index: 242016 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1912087 (The Pile)

Max Activating Token Index: 410

Text #11

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1336690 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4333. Min Act: -0.0000

Data Index: 148607 (The Pile)

Max Activating Token Index: 670

Text #13

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4307. Min Act: 0.0000

Data Index: 1366840 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4170. Min Act: -0.0000

Data Index: 298821 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4447. Min Act: -0.0000

Data Index: 120699 (The Pile)

Max Activating Token Index: 176

Text #16

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4292. Min Act: -0.0000

Data Index: 1369223 (The Pile)

Max Activating Token Index: 362

Text #17

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1533178 (The Pile)

Max Activating Token Index: 763

Text #18

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1581297 (The Pile)

Max Activating Token Index: 517

Text #19

Max Range: 0.5997. Min Range: -0.5997

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1110026 (The Pile)

Max Activating Token Index: 276