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

Dataset: The Pile

Neuron 2968 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: 0.8485. Min Range: -0.8485

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1669392 (The Pile)

Max Activating Token Index: 50

Text #1

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1346495 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7150. Min Act: -0.0000

Data Index: 426027 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1492018 (The Pile)

Max Activating Token Index: 852

Text #4

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6202. Min Act: -0.0000

Data Index: 1175745 (The Pile)

Max Activating Token Index: 847

Text #5

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6274. Min Act: -0.0000

Data Index: 1673266 (The Pile)

Max Activating Token Index: 943

Text #6

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7130. Min Act: -0.0000

Data Index: 54147 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6608. Min Act: -0.0000

Data Index: 425135 (The Pile)

Max Activating Token Index: 575

Text #8

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6984. Min Act: -0.0000

Data Index: 1452776 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.7101. Min Act: -0.0000

Data Index: 219871 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5822. Min Act: -0.0000

Data Index: 797672 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1384487 (The Pile)

Max Activating Token Index: 448

Text #12

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5901. Min Act: -0.0000

Data Index: 907040 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1198118 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5505. Min Act: -0.0000

Data Index: 956303 (The Pile)

Max Activating Token Index: 425

Text #15

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5660. Min Act: -0.0000

Data Index: 609567 (The Pile)

Max Activating Token Index: 946

Text #16

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5588. Min Act: -0.0000

Data Index: 663452 (The Pile)

Max Activating Token Index: 854

Text #17

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.6438. Min Act: -0.0000

Data Index: 671066 (The Pile)

Max Activating Token Index: 774

Text #18

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5572. Min Act: -0.0000

Data Index: 623475 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 0.8485. Min Range: -0.8485

Max Act: 0.5321. Min Act: -0.0000

Data Index: 1331284 (The Pile)

Max Activating Token Index: 968