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

Dataset: The Pile

Neuron 4972 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.4818. Min Act: -0.0000

Data Index: 1306528 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2983. Min Act: -0.0000

Data Index: 624006 (The Pile)

Max Activating Token Index: 467

Text #2

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3800. Min Act: -0.0000

Data Index: 1539623 (The Pile)

Max Activating Token Index: 331

Text #3

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1660680 (The Pile)

Max Activating Token Index: 721

Text #4

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.4012. Min Act: -0.0000

Data Index: 1523461 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1549831 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2185. Min Act: -0.0000

Data Index: 1746335 (The Pile)

Max Activating Token Index: 775

Text #7

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1543260 (The Pile)

Max Activating Token Index: 617

Text #8

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2420. Min Act: -0.0000

Data Index: 1111441 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2282. Min Act: -0.0000

Data Index: 1248067 (The Pile)

Max Activating Token Index: 839

Text #10

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.2129. Min Act: -0.0000

Data Index: 64378 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1316. Min Act: -0.0000

Data Index: 1842254 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1032. Min Act: -0.0000

Data Index: 300824 (The Pile)

Max Activating Token Index: 475

Text #13

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1128. Min Act: -0.0000

Data Index: 1558027 (The Pile)

Max Activating Token Index: 347

Text #14

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1674. Min Act: -0.0000

Data Index: 341937 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1009. Min Act: -0.0000

Data Index: 1551345 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0718. Min Act: -0.0000

Data Index: 1689509 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1490343 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.1330. Min Act: -0.0000

Data Index: 1223910 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 1.4818. Min Range: -1.4818

Max Act: 1.0296. Min Act: -0.0000

Data Index: 1311386 (The Pile)

Max Activating Token Index: 694