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

Dataset: The Pile

Neuron 459 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9924. Min Act: -0.0000

Data Index: 374272 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9661. Min Act: -0.0000

Data Index: 253440 (The Pile)

Max Activating Token Index: 447

Text #2

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9001. Min Act: -0.0000

Data Index: 239274 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8390. Min Act: -0.0000

Data Index: 65138 (The Pile)

Max Activating Token Index: 746

Text #4

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1522328 (The Pile)

Max Activating Token Index: 381

Text #5

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8587. Min Act: -0.0000

Data Index: 1982740 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9088. Min Act: -0.0000

Data Index: 1300900 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1507331 (The Pile)

Max Activating Token Index: 9

Text #8

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1062693 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8653. Min Act: -0.0000

Data Index: 621297 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1197051 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8588. Min Act: -0.0000

Data Index: 845649 (The Pile)

Max Activating Token Index: 139

Text #12

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8970. Min Act: -0.0000

Data Index: 1202550 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1774767 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8371. Min Act: -0.0000

Data Index: 1218333 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8179. Min Act: -0.0000

Data Index: 1871130 (The Pile)

Max Activating Token Index: 466

Text #16

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8125. Min Act: -0.0000

Data Index: 502511 (The Pile)

Max Activating Token Index: 497

Text #17

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8582. Min Act: -0.0000

Data Index: 539063 (The Pile)

Max Activating Token Index: 498

Text #18

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.8097. Min Act: -0.0000

Data Index: 801431 (The Pile)

Max Activating Token Index: 184

Text #19

Max Range: 0.9924. Min Range: -0.9924

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1520357 (The Pile)

Max Activating Token Index: 529