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

Dataset: The Pile

Neuron 2482 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7512. Min Act: -0.0000

Data Index: 337322 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7931. Min Act: -0.0000

Data Index: 978039 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7020. Min Act: -0.0000

Data Index: 1960990 (The Pile)

Max Activating Token Index: 250

Text #3

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7846. Min Act: -0.0000

Data Index: 495233 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.7254. Min Act: -0.0000

Data Index: 442981 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1266392 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6544. Min Act: -0.0000

Data Index: 88573 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6170. Min Act: -0.0000

Data Index: 1768042 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6319. Min Act: -0.0000

Data Index: 1444821 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1176746 (The Pile)

Max Activating Token Index: 332

Text #10

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6580. Min Act: -0.0000

Data Index: 924459 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5975. Min Act: -0.0000

Data Index: 376649 (The Pile)

Max Activating Token Index: 388

Text #12

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5800. Min Act: -0.0000

Data Index: 455120 (The Pile)

Max Activating Token Index: 335

Text #13

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1393152 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5864. Min Act: -0.0000

Data Index: 808615 (The Pile)

Max Activating Token Index: 310

Text #15

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1896911 (The Pile)

Max Activating Token Index: 317

Text #16

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5888. Min Act: -0.0000

Data Index: 1912531 (The Pile)

Max Activating Token Index: 676

Text #17

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1183757 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5799. Min Act: -0.0000

Data Index: 1789894 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.7931. Min Range: -0.7931

Max Act: 0.5725. Min Act: -0.0000

Data Index: 515614 (The Pile)

Max Activating Token Index: 266