Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1201 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.7553. Min Act: -0.0000

Data Index: 445157 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6791. Min Act: -0.0000

Data Index: 203218 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1330848 (The Pile)

Max Activating Token Index: 195

Text #3

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6387. Min Act: -0.0000

Data Index: 261813 (The Pile)

Max Activating Token Index: 787

Text #4

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1631176 (The Pile)

Max Activating Token Index: 921

Text #5

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1671492 (The Pile)

Max Activating Token Index: 432

Text #6

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5769. Min Act: 0.0000

Data Index: 1104810 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1421248 (The Pile)

Max Activating Token Index: 610

Text #8

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1577815 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1305198 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5836. Min Act: -0.0000

Data Index: 1610399 (The Pile)

Max Activating Token Index: 721

Text #11

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1709115 (The Pile)

Max Activating Token Index: 783

Text #12

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5397. Min Act: -0.0000

Data Index: 891210 (The Pile)

Max Activating Token Index: 312

Text #13

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5510. Min Act: -0.0000

Data Index: 1465781 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1443941 (The Pile)

Max Activating Token Index: 697

Text #15

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1069290 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5229. Min Act: 0.0000

Data Index: 1264280 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1099710 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5126. Min Act: 0.0001

Data Index: 1683097 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 0.7553. Min Range: -0.7553

Max Act: 0.5145. Min Act: -0.0000

Data Index: 469180 (The Pile)

Max Activating Token Index: 760