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

Dataset: The Pile

Neuron 2522 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: 1.9164. Min Range: -1.9164

Max Act: 1.9164. Min Act: -0.0000

Data Index: 7134 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.7105. Min Act: -0.0000

Data Index: 171149 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.6117. Min Act: -0.0000

Data Index: 1329671 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.5065. Min Act: -0.0000

Data Index: 733157 (The Pile)

Max Activating Token Index: 686

Text #4

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4400. Min Act: -0.0000

Data Index: 1258921 (The Pile)

Max Activating Token Index: 726

Text #5

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.5219. Min Act: -0.0000

Data Index: 136039 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.5049. Min Act: -0.0000

Data Index: 1351881 (The Pile)

Max Activating Token Index: 556

Text #7

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4987. Min Act: -0.0000

Data Index: 854380 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4882. Min Act: -0.0000

Data Index: 522505 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4716. Min Act: -0.0000

Data Index: 541910 (The Pile)

Max Activating Token Index: 374

Text #10

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4756. Min Act: -0.0000

Data Index: 1044371 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4608. Min Act: -0.0000

Data Index: 83387 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4925. Min Act: -0.0000

Data Index: 980042 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1505395 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.3914. Min Act: -0.0000

Data Index: 847047 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4776. Min Act: -0.0000

Data Index: 1849429 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.3935. Min Act: -0.0000

Data Index: 1694002 (The Pile)

Max Activating Token Index: 994

Text #17

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4217. Min Act: -0.0000

Data Index: 867898 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4237. Min Act: -0.0000

Data Index: 155163 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 1.9164. Min Range: -1.9164

Max Act: 1.4330. Min Act: -0.0000

Data Index: 1319100 (The Pile)

Max Activating Token Index: 922