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

Dataset: The Pile

Neuron 4817 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.8804. Min Act: -0.0000

Data Index: 178812 (The Pile)

Max Activating Token Index: 288

Text #1

Max Range: 7.2056. Min Range: -7.2056

Max Act: 7.2056. Min Act: -0.0000

Data Index: 1015269 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.3483. Min Act: -0.0000

Data Index: 898875 (The Pile)

Max Activating Token Index: 409

Text #3

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.7380. Min Act: -0.0000

Data Index: 1221857 (The Pile)

Max Activating Token Index: 821

Text #4

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.1100. Min Act: -0.0000

Data Index: 1754434 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.8522. Min Act: -0.0000

Data Index: 1683238 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.6478. Min Act: -0.0000

Data Index: 299958 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.1761. Min Act: -0.0000

Data Index: 1772803 (The Pile)

Max Activating Token Index: 229

Text #8

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.7692. Min Act: -0.0000

Data Index: 1403644 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.9200. Min Act: -0.0000

Data Index: 1015524 (The Pile)

Max Activating Token Index: 259

Text #10

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.5688. Min Act: -0.0000

Data Index: 1631917 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.7146. Min Act: -0.0000

Data Index: 1753254 (The Pile)

Max Activating Token Index: 456

Text #12

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.3979. Min Act: -0.0000

Data Index: 1371734 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.4513. Min Act: -0.0000

Data Index: 1236456 (The Pile)

Max Activating Token Index: 714

Text #14

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.1886. Min Act: -0.0000

Data Index: 1748015 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.1729. Min Act: -0.0000

Data Index: 750128 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.3965. Min Act: -0.0000

Data Index: 1137450 (The Pile)

Max Activating Token Index: 952

Text #17

Max Range: 7.2056. Min Range: -7.2056

Max Act: 6.1191. Min Act: -0.0000

Data Index: 1794003 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.9004. Min Act: -0.0000

Data Index: 1887304 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 7.2056. Min Range: -7.2056

Max Act: 5.7601. Min Act: -0.0000

Data Index: 1676676 (The Pile)

Max Activating Token Index: 614