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

Dataset: The Pile

Neuron 147 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: 1.5401. Min Range: -1.5401

Max Act: 1.5401. Min Act: -0.0000

Data Index: 1866193 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3628. Min Act: -0.0000

Data Index: 1221725 (The Pile)

Max Activating Token Index: 793

Text #2

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4015. Min Act: -0.0000

Data Index: 1727845 (The Pile)

Max Activating Token Index: 665

Text #3

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4737. Min Act: -0.0000

Data Index: 359810 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4424. Min Act: -0.0000

Data Index: 633118 (The Pile)

Max Activating Token Index: 1008

Text #5

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3113. Min Act: -0.0000

Data Index: 1024657 (The Pile)

Max Activating Token Index: 36

Text #6

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2679. Min Act: -0.0000

Data Index: 780799 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.4107. Min Act: -0.0000

Data Index: 1308436 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3248. Min Act: -0.0000

Data Index: 1806037 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3838. Min Act: -0.0000

Data Index: 604448 (The Pile)

Max Activating Token Index: 560

Text #10

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.3847. Min Act: -0.0000

Data Index: 610781 (The Pile)

Max Activating Token Index: 571

Text #11

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2957. Min Act: -0.0000

Data Index: 1934052 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1908040 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2148. Min Act: -0.0000

Data Index: 926167 (The Pile)

Max Activating Token Index: 275

Text #14

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2589. Min Act: -0.0000

Data Index: 1348159 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2320. Min Act: -0.0000

Data Index: 161974 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.1292. Min Act: -0.0000

Data Index: 202466 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1922100 (The Pile)

Max Activating Token Index: 69

Text #18

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1003415 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 1.5401. Min Range: -1.5401

Max Act: 1.2123. Min Act: -0.0000

Data Index: 530094 (The Pile)

Max Activating Token Index: 766