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

Dataset: The Pile

Neuron 506 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: 3.3465. Min Range: -3.3465

Max Act: 3.0805. Min Act: -0.0000

Data Index: 113688 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 3.3465. Min Range: -3.3465

Max Act: 3.3465. Min Act: -0.0000

Data Index: 698466 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.9208. Min Act: -0.0000

Data Index: 433128 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.6537. Min Act: -0.0000

Data Index: 900966 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.7304. Min Act: -0.0000

Data Index: 336417 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.6010. Min Act: -0.0000

Data Index: 174745 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.8596. Min Act: -0.0000

Data Index: 88164 (The Pile)

Max Activating Token Index: 293

Text #7

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.7169. Min Act: -0.0000

Data Index: 1146244 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.8057. Min Act: -0.0000

Data Index: 1411478 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.8852. Min Act: -0.0000

Data Index: 1772868 (The Pile)

Max Activating Token Index: 624

Text #10

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.5942. Min Act: -0.0000

Data Index: 356892 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.7208. Min Act: -0.0000

Data Index: 186325 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.6535. Min Act: -0.0000

Data Index: 1871516 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.6710. Min Act: -0.0000

Data Index: 1401529 (The Pile)

Max Activating Token Index: 433

Text #14

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.6690. Min Act: -0.0000

Data Index: 1651169 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.5252. Min Act: -0.0000

Data Index: 849381 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.7856. Min Act: -0.0000

Data Index: 1735275 (The Pile)

Max Activating Token Index: 415

Text #17

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.4860. Min Act: -0.0000

Data Index: 1127811 (The Pile)

Max Activating Token Index: 628

Text #18

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.7662. Min Act: -0.0000

Data Index: 1489449 (The Pile)

Max Activating Token Index: 490

Text #19

Max Range: 3.3465. Min Range: -3.3465

Max Act: 2.6525. Min Act: -0.0000

Data Index: 513873 (The Pile)

Max Activating Token Index: 539