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

Dataset: The Pile

Neuron 4079 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6835. Min Act: -0.0000

Data Index: 33123 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1181020 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5881. Min Act: 0.0000

Data Index: 429800 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5546. Min Act: 0.0000

Data Index: 522228 (The Pile)

Max Activating Token Index: 64

Text #4

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5306. Min Act: -0.0000

Data Index: 1904173 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5219. Min Act: -0.0000

Data Index: 1954949 (The Pile)

Max Activating Token Index: 118

Text #6

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1206146 (The Pile)

Max Activating Token Index: 616

Text #7

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4937. Min Act: -0.0000

Data Index: 194913 (The Pile)

Max Activating Token Index: 929

Text #8

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5095. Min Act: -0.0000

Data Index: 295578 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5110. Min Act: -0.0000

Data Index: 302149 (The Pile)

Max Activating Token Index: 895

Text #10

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.5186. Min Act: -0.0000

Data Index: 918110 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4967. Min Act: -0.0000

Data Index: 1098667 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4791. Min Act: -0.0000

Data Index: 1338848 (The Pile)

Max Activating Token Index: 236

Text #13

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1083175 (The Pile)

Max Activating Token Index: 74

Text #14

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4386. Min Act: -0.0000

Data Index: 573869 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4831. Min Act: -0.0000

Data Index: 409820 (The Pile)

Max Activating Token Index: 978

Text #16

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4827. Min Act: -0.0000

Data Index: 798552 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4631. Min Act: -0.0000

Data Index: 1915479 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4469. Min Act: -0.0000

Data Index: 245176 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 0.6835. Min Range: -0.6835

Max Act: 0.4624. Min Act: -0.0000

Data Index: 827100 (The Pile)

Max Activating Token Index: 269