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

Dataset: The Pile

Neuron 1954 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: 0.9295. Min Range: -0.9295

Max Act: 0.9295. Min Act: -0.0000

Data Index: 23256 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1614960 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.6427. Min Act: -0.0000

Data Index: 1105977 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5642. Min Act: -0.0000

Data Index: 184969 (The Pile)

Max Activating Token Index: 427

Text #4

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5891. Min Act: 0.0000

Data Index: 354059 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1228457 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5295. Min Act: -0.0000

Data Index: 997249 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5312. Min Act: -0.0000

Data Index: 773259 (The Pile)

Max Activating Token Index: 390

Text #8

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5205. Min Act: -0.0000

Data Index: 670809 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4871. Min Act: -0.0000

Data Index: 118321 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4769. Min Act: -0.0000

Data Index: 248807 (The Pile)

Max Activating Token Index: 1021

Text #11

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.5114. Min Act: -0.0000

Data Index: 588470 (The Pile)

Max Activating Token Index: 356

Text #12

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4478. Min Act: -0.0000

Data Index: 279877 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4801. Min Act: -0.0000

Data Index: 440753 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4400. Min Act: 0.0000

Data Index: 1440994 (The Pile)

Max Activating Token Index: 206

Text #15

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4610. Min Act: -0.0000

Data Index: 1922546 (The Pile)

Max Activating Token Index: 927

Text #16

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1845763 (The Pile)

Max Activating Token Index: 322

Text #17

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4529. Min Act: 0.0000

Data Index: 1730706 (The Pile)

Max Activating Token Index: 803

Text #18

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1872174 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 0.9295. Min Range: -0.9295

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1467376 (The Pile)

Max Activating Token Index: 916