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

Dataset: The Pile

Neuron 2940 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: 5.7746. Min Range: -5.7746

Max Act: 5.7746. Min Act: -0.0000

Data Index: 1122370 (The Pile)

Max Activating Token Index: 691

Text #1

Max Range: 5.7746. Min Range: -5.7746

Max Act: 5.3451. Min Act: -0.0000

Data Index: 617325 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 5.7746. Min Range: -5.7746

Max Act: 5.6666. Min Act: -0.0000

Data Index: 1269331 (The Pile)

Max Activating Token Index: 479

Text #3

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.8770. Min Act: -0.0000

Data Index: 657424 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.7457. Min Act: -0.0000

Data Index: 582817 (The Pile)

Max Activating Token Index: 907

Text #5

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.1300. Min Act: -0.0000

Data Index: 307090 (The Pile)

Max Activating Token Index: 310

Text #6

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2829. Min Act: -0.0000

Data Index: 1519091 (The Pile)

Max Activating Token Index: 561

Text #7

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.3842. Min Act: -0.0000

Data Index: 125187 (The Pile)

Max Activating Token Index: 348

Text #8

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.3394. Min Act: -0.0000

Data Index: 492644 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.9575. Min Act: -0.0000

Data Index: 906110 (The Pile)

Max Activating Token Index: 791

Text #10

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2831. Min Act: -0.0000

Data Index: 401708 (The Pile)

Max Activating Token Index: 258

Text #11

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2711. Min Act: -0.0000

Data Index: 1304988 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2444. Min Act: -0.0000

Data Index: 659035 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2393. Min Act: -0.0000

Data Index: 1480479 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2046. Min Act: -0.0000

Data Index: 130874 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.3762. Min Act: -0.0000

Data Index: 834968 (The Pile)

Max Activating Token Index: 529

Text #16

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.1392. Min Act: -0.0000

Data Index: 993615 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.1349. Min Act: -0.0000

Data Index: 1372723 (The Pile)

Max Activating Token Index: 178

Text #18

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.9393. Min Act: -0.0000

Data Index: 1703286 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.1134. Min Act: -0.0000

Data Index: 1289658 (The Pile)

Max Activating Token Index: 150