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

Dataset: The Pile

Neuron 2019 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: 0.8683. Min Range: -0.8683

Max Act: 0.8489. Min Act: -0.0000

Data Index: 257948 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7153. Min Act: -0.0000

Data Index: 1524150 (The Pile)

Max Activating Token Index: 615

Text #2

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8183. Min Act: -0.0000

Data Index: 165691 (The Pile)

Max Activating Token Index: 207

Text #3

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7985. Min Act: -0.0000

Data Index: 141323 (The Pile)

Max Activating Token Index: 899

Text #4

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8210. Min Act: -0.0000

Data Index: 950904 (The Pile)

Max Activating Token Index: 713

Text #5

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1783180 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8683. Min Act: -0.0000

Data Index: 765404 (The Pile)

Max Activating Token Index: 773

Text #7

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1440270 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7849. Min Act: -0.0000

Data Index: 568752 (The Pile)

Max Activating Token Index: 486

Text #9

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8125. Min Act: -0.0000

Data Index: 6013 (The Pile)

Max Activating Token Index: 566

Text #10

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7118. Min Act: -0.0000

Data Index: 919401 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1817568 (The Pile)

Max Activating Token Index: 145

Text #12

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7265. Min Act: -0.0000

Data Index: 425849 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1824640 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6342. Min Act: -0.0000

Data Index: 615267 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7745. Min Act: -0.0000

Data Index: 1665393 (The Pile)

Max Activating Token Index: 598

Text #16

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6885. Min Act: -0.0000

Data Index: 1672807 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6192. Min Act: -0.0000

Data Index: 114102 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1896826 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 0.8683. Min Range: -0.8683

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1178954 (The Pile)

Max Activating Token Index: 940