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

Dataset: The Pile

Neuron 2818 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.8004. Min Act: -0.0000

Data Index: 1876647 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6780. Min Act: -0.0000

Data Index: 614716 (The Pile)

Max Activating Token Index: 960

Text #2

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6086. Min Act: -0.0000

Data Index: 256107 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6345. Min Act: -0.0000

Data Index: 616349 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1300578 (The Pile)

Max Activating Token Index: 117

Text #5

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1369254 (The Pile)

Max Activating Token Index: 837

Text #6

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1865069 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5906. Min Act: -0.0000

Data Index: 869917 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1859821 (The Pile)

Max Activating Token Index: 925

Text #9

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5924. Min Act: -0.0000

Data Index: 966989 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5927. Min Act: -0.0000

Data Index: 612515 (The Pile)

Max Activating Token Index: 101

Text #11

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5936. Min Act: -0.0000

Data Index: 178118 (The Pile)

Max Activating Token Index: 647

Text #12

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5670. Min Act: -0.0000

Data Index: 1505349 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5590. Min Act: -0.0000

Data Index: 1319885 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5591. Min Act: -0.0000

Data Index: 199733 (The Pile)

Max Activating Token Index: 384

Text #15

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1293374 (The Pile)

Max Activating Token Index: 1001

Text #16

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5538. Min Act: -0.0000

Data Index: 767049 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1177298 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1208931 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.8004. Min Range: -0.8004

Max Act: 0.5585. Min Act: -0.0000

Data Index: 1651096 (The Pile)

Max Activating Token Index: 70