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

Dataset: The Pile

Neuron 4282 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: 5.1490. Min Range: -5.1490

Max Act: 5.1490. Min Act: -0.0000

Data Index: 589396 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.9893. Min Act: -0.0000

Data Index: 1204298 (The Pile)

Max Activating Token Index: 565

Text #2

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.9158. Min Act: -0.0000

Data Index: 1230568 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.7182. Min Act: -0.0000

Data Index: 342713 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 5.1490. Min Range: -5.1490

Max Act: 4.1788. Min Act: -0.0000

Data Index: 1575370 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.8029. Min Act: -0.0000

Data Index: 949379 (The Pile)

Max Activating Token Index: 332

Text #6

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.7040. Min Act: -0.0000

Data Index: 246468 (The Pile)

Max Activating Token Index: 288

Text #7

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.8685. Min Act: -0.0000

Data Index: 234736 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.6448. Min Act: -0.0000

Data Index: 1393658 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 5.1490. Min Range: -5.1490

Max Act: 4.2782. Min Act: -0.0000

Data Index: 926153 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.4515. Min Act: -0.0000

Data Index: 1981762 (The Pile)

Max Activating Token Index: 883

Text #11

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.6148. Min Act: -0.0000

Data Index: 694269 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.5699. Min Act: -0.0000

Data Index: 1548490 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.7796. Min Act: -0.0000

Data Index: 1996697 (The Pile)

Max Activating Token Index: 54

Text #14

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.1534. Min Act: -0.0000

Data Index: 1178664 (The Pile)

Max Activating Token Index: 491

Text #15

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.5146. Min Act: -0.0000

Data Index: 865507 (The Pile)

Max Activating Token Index: 193

Text #16

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.5145. Min Act: -0.0000

Data Index: 245200 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.0344. Min Act: -0.0000

Data Index: 1143399 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.2312. Min Act: -0.0000

Data Index: 710346 (The Pile)

Max Activating Token Index: 445

Text #19

Max Range: 5.1490. Min Range: -5.1490

Max Act: 3.3683. Min Act: -0.0000

Data Index: 1530179 (The Pile)

Max Activating Token Index: 444