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

Dataset: The Pile

Neuron 2471 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: 0.6188. Min Range: -0.6188

Max Act: 0.6188. Min Act: -0.0000

Data Index: 475112 (The Pile)

Max Activating Token Index: 175

Text #1

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1044942 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1940383 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5125. Min Act: -0.0000

Data Index: 203957 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1189964 (The Pile)

Max Activating Token Index: 593

Text #5

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1486817 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4442. Min Act: -0.0000

Data Index: 185279 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1132796 (The Pile)

Max Activating Token Index: 51

Text #8

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4808. Min Act: -0.0000

Data Index: 1413683 (The Pile)

Max Activating Token Index: 707

Text #9

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1816852 (The Pile)

Max Activating Token Index: 222

Text #10

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4629. Min Act: -0.0000

Data Index: 231711 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4450. Min Act: -0.0000

Data Index: 488727 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4877. Min Act: -0.0000

Data Index: 1247900 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1968428 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1106616 (The Pile)

Max Activating Token Index: 103

Text #15

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1667726 (The Pile)

Max Activating Token Index: 1004

Text #16

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1357885 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1113315 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1339590 (The Pile)

Max Activating Token Index: 697

Text #19

Max Range: 0.6188. Min Range: -0.6188

Max Act: 0.4382. Min Act: -0.0000

Data Index: 907471 (The Pile)

Max Activating Token Index: 639