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

Dataset: The Pile

Neuron 4090 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: 1.4748. Min Range: -1.4748

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1585612 (The Pile)

Max Activating Token Index: 131

Text #1

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.4748. Min Act: -0.0000

Data Index: 1320179 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3747. Min Act: -0.0000

Data Index: 343347 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3345. Min Act: -0.0000

Data Index: 336847 (The Pile)

Max Activating Token Index: 236

Text #4

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1722490 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2024. Min Act: -0.0000

Data Index: 1958722 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1517. Min Act: -0.0000

Data Index: 1842516 (The Pile)

Max Activating Token Index: 989

Text #7

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2130. Min Act: -0.0000

Data Index: 1748369 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2878. Min Act: 0.0000

Data Index: 1772469 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1726. Min Act: -0.0000

Data Index: 1544932 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1234. Min Act: -0.0000

Data Index: 1233024 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2361. Min Act: -0.0000

Data Index: 1161654 (The Pile)

Max Activating Token Index: 733

Text #12

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.2617. Min Act: -0.0000

Data Index: 1116604 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3759. Min Act: -0.0000

Data Index: 1246841 (The Pile)

Max Activating Token Index: 643

Text #14

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1560. Min Act: -0.0000

Data Index: 880180 (The Pile)

Max Activating Token Index: 410

Text #15

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1338036 (The Pile)

Max Activating Token Index: 262

Text #16

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1143. Min Act: -0.0000

Data Index: 1695857 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1354. Min Act: -0.0000

Data Index: 366123 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0774. Min Act: -0.0000

Data Index: 833759 (The Pile)

Max Activating Token Index: 977

Text #19

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1274. Min Act: -0.0000

Data Index: 570951 (The Pile)

Max Activating Token Index: 788