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

Dataset: The Pile

Neuron 839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.1042. Min Act: -0.0000

Data Index: 1147305 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.2053. Min Act: -0.0000

Data Index: 959517 (The Pile)

Max Activating Token Index: 605

Text #2

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.1530. Min Act: -0.0000

Data Index: 848840 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.1127. Min Act: -0.0000

Data Index: 1273567 (The Pile)

Max Activating Token Index: 342

Text #4

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.9928. Min Act: -0.0000

Data Index: 781573 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.0546. Min Act: -0.0000

Data Index: 1365837 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.1187. Min Act: -0.0000

Data Index: 1876708 (The Pile)

Max Activating Token Index: 900

Text #7

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.1065. Min Act: -0.0000

Data Index: 1561056 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.8552. Min Act: -0.0000

Data Index: 344939 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.0567. Min Act: -0.0000

Data Index: 1758408 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.8461. Min Act: -0.0000

Data Index: 807538 (The Pile)

Max Activating Token Index: 371

Text #11

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.8397. Min Act: -0.0000

Data Index: 1358862 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.7539. Min Act: -0.0000

Data Index: 1951877 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.9314. Min Act: -0.0000

Data Index: 293594 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.7103. Min Act: -0.0000

Data Index: 274942 (The Pile)

Max Activating Token Index: 714

Text #15

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.6197. Min Act: -0.0000

Data Index: 1612143 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.8880. Min Act: -0.0000

Data Index: 498939 (The Pile)

Max Activating Token Index: 186

Text #17

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.7788. Min Act: -0.0000

Data Index: 1562677 (The Pile)

Max Activating Token Index: 249

Text #18

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.8962. Min Act: -0.0000

Data Index: 853361 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 3.1042. Min Range: -3.1042

Max Act: 1.7724. Min Act: -0.0000

Data Index: 606676 (The Pile)

Max Activating Token Index: 442