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

Dataset: The Pile

Neuron 2308 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: 3.8633. Min Range: -3.8633

Max Act: 3.8633. Min Act: -0.0000

Data Index: 1592775 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 3.8633. Min Range: -3.8633

Max Act: 3.7418. Min Act: -0.0000

Data Index: 1811281 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 3.8633. Min Range: -3.8633

Max Act: 3.0934. Min Act: -0.0000

Data Index: 772892 (The Pile)

Max Activating Token Index: 396

Text #3

Max Range: 3.8633. Min Range: -3.8633

Max Act: 3.2342. Min Act: -0.0000

Data Index: 1856150 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 3.8633. Min Range: -3.8633

Max Act: 3.1751. Min Act: -0.0000

Data Index: 573545 (The Pile)

Max Activating Token Index: 443

Text #5

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.8064. Min Act: -0.0000

Data Index: 1672299 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.9869. Min Act: -0.0000

Data Index: 1725527 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 3.8633. Min Range: -3.8633

Max Act: 3.1444. Min Act: -0.0000

Data Index: 525098 (The Pile)

Max Activating Token Index: 107

Text #8

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.9865. Min Act: -0.0000

Data Index: 856064 (The Pile)

Max Activating Token Index: 469

Text #9

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.9343. Min Act: -0.0000

Data Index: 217548 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.8802. Min Act: -0.0000

Data Index: 1673998 (The Pile)

Max Activating Token Index: 690

Text #11

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.8945. Min Act: -0.0000

Data Index: 466906 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.6617. Min Act: -0.0000

Data Index: 1789880 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.8878. Min Act: -0.0000

Data Index: 287902 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.9435. Min Act: -0.0000

Data Index: 512027 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.6205. Min Act: -0.0000

Data Index: 1928259 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.7295. Min Act: -0.0000

Data Index: 1151500 (The Pile)

Max Activating Token Index: 91

Text #17

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.5973. Min Act: -0.0000

Data Index: 1458127 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.8960. Min Act: -0.0000

Data Index: 1750326 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 3.8633. Min Range: -3.8633

Max Act: 2.7415. Min Act: -0.0000

Data Index: 1295703 (The Pile)

Max Activating Token Index: 72