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

Dataset: The Pile

Neuron 3658 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.5700. Min Act: -0.0000

Data Index: 1277361 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.4846. Min Act: -0.0000

Data Index: 1004942 (The Pile)

Max Activating Token Index: 186

Text #2

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3210. Min Act: -0.0000

Data Index: 44372 (The Pile)

Max Activating Token Index: 223

Text #3

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.4772. Min Act: -0.0000

Data Index: 1081148 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2894. Min Act: -0.0000

Data Index: 1232226 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.4273. Min Act: -0.0000

Data Index: 1110149 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3864. Min Act: -0.0000

Data Index: 1755325 (The Pile)

Max Activating Token Index: 538

Text #7

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3870. Min Act: -0.0000

Data Index: 522167 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3447. Min Act: -0.0000

Data Index: 552951 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.4569. Min Act: -0.0000

Data Index: 686250 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3111. Min Act: -0.0000

Data Index: 478915 (The Pile)

Max Activating Token Index: 318

Text #11

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.5800. Min Act: -0.0000

Data Index: 449736 (The Pile)

Max Activating Token Index: 382

Text #12

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.2674. Min Act: -0.0000

Data Index: 1356869 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.0632. Min Act: -0.0000

Data Index: 1797412 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3904. Min Act: -0.0000

Data Index: 907869 (The Pile)

Max Activating Token Index: 486

Text #15

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3909. Min Act: -0.0000

Data Index: 1632251 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 3.5800. Min Range: -3.5800

Max Act: 2.9340. Min Act: -0.0000

Data Index: 1133233 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.1999. Min Act: -0.0000

Data Index: 1726260 (The Pile)

Max Activating Token Index: 998

Text #18

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.3633. Min Act: -0.0000

Data Index: 429466 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 3.5800. Min Range: -3.5800

Max Act: 3.0553. Min Act: -0.0000

Data Index: 954685 (The Pile)

Max Activating Token Index: 984