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

Dataset: The Pile

Neuron 1122 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: 0.2532. Min Range: -0.2532

Max Act: 0.2472. Min Act: -0.0000

Data Index: 1357717 (The Pile)

Max Activating Token Index: 921

Text #1

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2430. Min Act: -0.0000

Data Index: 446750 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2512. Min Act: -0.0000

Data Index: 375263 (The Pile)

Max Activating Token Index: 847

Text #3

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2532. Min Act: -0.0000

Data Index: 700399 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1732073 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.2138. Min Act: -0.0000

Data Index: 553339 (The Pile)

Max Activating Token Index: 482

Text #6

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1414132 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1730819 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1579700 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1864. Min Act: -0.0000

Data Index: 629457 (The Pile)

Max Activating Token Index: 136

Text #10

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1707927 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1969. Min Act: -0.0000

Data Index: 415051 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1951. Min Act: -0.0000

Data Index: 568629 (The Pile)

Max Activating Token Index: 11

Text #13

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1356722 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1801. Min Act: -0.0000

Data Index: 921812 (The Pile)

Max Activating Token Index: 526

Text #15

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1144461 (The Pile)

Max Activating Token Index: 5

Text #16

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1997. Min Act: -0.0000

Data Index: 601495 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1874. Min Act: -0.0000

Data Index: 861054 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1597. Min Act: -0.0000

Data Index: 973471 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 0.2532. Min Range: -0.2532

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1784015 (The Pile)

Max Activating Token Index: 299