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

Dataset: The Pile

Neuron 3606 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: 7.8424. Min Range: -7.8424

Max Act: 7.8424. Min Act: -0.0000

Data Index: 619538 (The Pile)

Max Activating Token Index: 893

Text #1

Max Range: 7.8424. Min Range: -7.8424

Max Act: 7.6559. Min Act: -0.0000

Data Index: 1502441 (The Pile)

Max Activating Token Index: 468

Text #2

Max Range: 7.8424. Min Range: -7.8424

Max Act: 7.6778. Min Act: -0.0000

Data Index: 1907415 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 7.8424. Min Range: -7.8424

Max Act: 7.1915. Min Act: -0.0000

Data Index: 711357 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 7.8424. Min Range: -7.8424

Max Act: 6.9608. Min Act: -0.0000

Data Index: 960805 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 7.8424. Min Range: -7.8424

Max Act: 6.9756. Min Act: -0.0000

Data Index: 1082763 (The Pile)

Max Activating Token Index: 688

Text #6

Max Range: 7.8424. Min Range: -7.8424

Max Act: 6.5944. Min Act: -0.0000

Data Index: 1737079 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 7.8424. Min Range: -7.8424

Max Act: 6.9802. Min Act: -0.0000

Data Index: 1467832 (The Pile)

Max Activating Token Index: 856

Text #8

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.5272. Min Act: -0.0000

Data Index: 162202 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 7.8424. Min Range: -7.8424

Max Act: 6.1296. Min Act: -0.0000

Data Index: 1474118 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.5517. Min Act: -0.0000

Data Index: 1702119 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.3169. Min Act: -0.0000

Data Index: 1725830 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.2726. Min Act: -0.0000

Data Index: 209079 (The Pile)

Max Activating Token Index: 359

Text #13

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.3566. Min Act: -0.0000

Data Index: 1362687 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.1185. Min Act: -0.0000

Data Index: 1133759 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.0667. Min Act: -0.0000

Data Index: 1978520 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 7.8424. Min Range: -7.8424

Max Act: 4.7499. Min Act: -0.0000

Data Index: 1233054 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.0143. Min Act: -0.0000

Data Index: 825555 (The Pile)

Max Activating Token Index: 678

Text #18

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.2140. Min Act: -0.0000

Data Index: 1137993 (The Pile)

Max Activating Token Index: 415

Text #19

Max Range: 7.8424. Min Range: -7.8424

Max Act: 5.1728. Min Act: -0.0000

Data Index: 1528697 (The Pile)

Max Activating Token Index: 349