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

Dataset: The Pile

Neuron 1808 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: 0.9408. Min Range: -0.9408

Max Act: 0.9408. Min Act: -0.0000

Data Index: 630759 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8561. Min Act: -0.0000

Data Index: 899369 (The Pile)

Max Activating Token Index: 999

Text #2

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.9195. Min Act: -0.0000

Data Index: 702364 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1048434 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8559. Min Act: -0.0000

Data Index: 978220 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1688211 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8586. Min Act: -0.0000

Data Index: 179688 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1732685 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8596. Min Act: -0.0000

Data Index: 1154476 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8215. Min Act: -0.0000

Data Index: 708031 (The Pile)

Max Activating Token Index: 171

Text #10

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8180. Min Act: -0.0000

Data Index: 507031 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1640388 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7752. Min Act: -0.0000

Data Index: 754644 (The Pile)

Max Activating Token Index: 956

Text #13

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1114254 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1773341 (The Pile)

Max Activating Token Index: 504

Text #15

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8038. Min Act: -0.0000

Data Index: 470373 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.8115. Min Act: -0.0000

Data Index: 1230187 (The Pile)

Max Activating Token Index: 421

Text #17

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1259993 (The Pile)

Max Activating Token Index: 41

Text #18

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.7777. Min Act: -0.0000

Data Index: 516378 (The Pile)

Max Activating Token Index: 252

Text #19

Max Range: 0.9408. Min Range: -0.9408

Max Act: 0.6833. Min Act: -0.0000

Data Index: 1565397 (The Pile)

Max Activating Token Index: 687