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

Dataset: The Pile

Neuron 676 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1427241 (The Pile)

Max Activating Token Index: 985

Text #1

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1628815 (The Pile)

Max Activating Token Index: 329

Text #2

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2508. Min Act: -0.0000

Data Index: 594055 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2319. Min Act: -0.0000

Data Index: 442411 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2173. Min Act: -0.0000

Data Index: 482984 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2064. Min Act: -0.0000

Data Index: 471656 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2379. Min Act: -0.0000

Data Index: 628455 (The Pile)

Max Activating Token Index: 946

Text #7

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2206. Min Act: -0.0000

Data Index: 650036 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2074. Min Act: -0.0000

Data Index: 761340 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1997248 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1904. Min Act: -0.0000

Data Index: 798725 (The Pile)

Max Activating Token Index: 583

Text #11

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1073929 (The Pile)

Max Activating Token Index: 902

Text #12

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1777. Min Act: -0.0000

Data Index: 1017266 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1919. Min Act: -0.0000

Data Index: 347848 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1817. Min Act: -0.0000

Data Index: 338623 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1830192 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1591. Min Act: -0.0000

Data Index: 661338 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1190725 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1519055 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1815. Min Act: -0.0000

Data Index: 707432 (The Pile)

Max Activating Token Index: 728