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

Dataset: The Pile

Neuron 2336 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: 0.5302. Min Range: -0.5302

Max Act: 0.5302. Min Act: -0.0000

Data Index: 1047030 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1536125 (The Pile)

Max Activating Token Index: 907

Text #2

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1892922 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4545. Min Act: -0.0000

Data Index: 1458417 (The Pile)

Max Activating Token Index: 810

Text #4

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1004531 (The Pile)

Max Activating Token Index: 865

Text #5

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4386. Min Act: -0.0000

Data Index: 1144556 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4488. Min Act: -0.0000

Data Index: 791380 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4700. Min Act: -0.0000

Data Index: 552567 (The Pile)

Max Activating Token Index: 665

Text #8

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1360825 (The Pile)

Max Activating Token Index: 249

Text #9

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4569. Min Act: -0.0000

Data Index: 739966 (The Pile)

Max Activating Token Index: 229

Text #10

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4162. Min Act: -0.0000

Data Index: 92988 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4503. Min Act: -0.0000

Data Index: 442207 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4031. Min Act: -0.0000

Data Index: 483936 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1653567 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4150. Min Act: -0.0000

Data Index: 431720 (The Pile)

Max Activating Token Index: 347

Text #15

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4110. Min Act: -0.0000

Data Index: 1002366 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1096621 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4114. Min Act: -0.0000

Data Index: 389956 (The Pile)

Max Activating Token Index: 563

Text #18

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3627. Min Act: -0.0000

Data Index: 50752 (The Pile)

Max Activating Token Index: 79

Text #19

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1851438 (The Pile)

Max Activating Token Index: 668