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

Dataset: The Pile

Neuron 2596 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: 1.1598. Min Range: -1.1598

Max Act: 1.1598. Min Act: -0.0000

Data Index: 1607398 (The Pile)

Max Activating Token Index: 103

Text #1

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.1185. Min Act: -0.0000

Data Index: 1746014 (The Pile)

Max Activating Token Index: 561

Text #2

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0481. Min Act: -0.0000

Data Index: 781521 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1700927 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0885. Min Act: -0.0000

Data Index: 552856 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.1229. Min Act: -0.0000

Data Index: 232337 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.1227. Min Act: -0.0000

Data Index: 1293611 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1014291 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0822. Min Act: -0.0000

Data Index: 1684362 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1282473 (The Pile)

Max Activating Token Index: 555

Text #10

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0435. Min Act: -0.0000

Data Index: 1183943 (The Pile)

Max Activating Token Index: 379

Text #11

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0761. Min Act: -0.0000

Data Index: 207223 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9671. Min Act: -0.0000

Data Index: 734009 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0313. Min Act: -0.0000

Data Index: 1092625 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1203188 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0244. Min Act: -0.0000

Data Index: 1652769 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 1.1598. Min Range: -1.1598

Max Act: 1.0512. Min Act: -0.0000

Data Index: 1769873 (The Pile)

Max Activating Token Index: 403

Text #17

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1187836 (The Pile)

Max Activating Token Index: 210

Text #18

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9982. Min Act: -0.0000

Data Index: 14267 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 1.1598. Min Range: -1.1598

Max Act: 0.9658. Min Act: -0.0000

Data Index: 1452459 (The Pile)

Max Activating Token Index: 957