Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2322 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.0156. Min Range: -3.0156

Max Act: 3.0156. Min Act: -0.0000

Data Index: 279154 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.7461. Min Act: -0.0000

Data Index: 1316630 (The Pile)

Max Activating Token Index: 903

Text #2

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.7093. Min Act: -0.0000

Data Index: 1171077 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.5128. Min Act: -0.0000

Data Index: 307775 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4186. Min Act: -0.0000

Data Index: 1094844 (The Pile)

Max Activating Token Index: 1015

Text #5

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4199. Min Act: -0.0000

Data Index: 1087760 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4056. Min Act: -0.0000

Data Index: 1701062 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.6541. Min Act: -0.0000

Data Index: 852762 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4816. Min Act: -0.0000

Data Index: 378431 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4848. Min Act: -0.0000

Data Index: 511554 (The Pile)

Max Activating Token Index: 785

Text #10

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.3679. Min Act: -0.0000

Data Index: 1312471 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4642. Min Act: -0.0000

Data Index: 551604 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.5604. Min Act: -0.0000

Data Index: 689078 (The Pile)

Max Activating Token Index: 987

Text #13

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4266. Min Act: -0.0000

Data Index: 1887590 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4244. Min Act: -0.0000

Data Index: 505594 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.5354. Min Act: -0.0000

Data Index: 319382 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4104. Min Act: -0.0000

Data Index: 913906 (The Pile)

Max Activating Token Index: 842

Text #17

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4095. Min Act: -0.0000

Data Index: 413204 (The Pile)

Max Activating Token Index: 960

Text #18

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.4122. Min Act: -0.0000

Data Index: 1315386 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 3.0156. Min Range: -3.0156

Max Act: 2.3943. Min Act: -0.0000

Data Index: 1380622 (The Pile)

Max Activating Token Index: 890