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

Dataset: The Pile

Neuron 1375 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: 1.6807. Min Range: -1.6807

Max Act: 1.5938. Min Act: -0.0000

Data Index: 1467639 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.6317. Min Act: -0.0000

Data Index: 240955 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.6807. Min Act: -0.0000

Data Index: 1220096 (The Pile)

Max Activating Token Index: 664

Text #3

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1923788 (The Pile)

Max Activating Token Index: 540

Text #4

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3433. Min Act: -0.0000

Data Index: 1825564 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.4504. Min Act: -0.0000

Data Index: 883587 (The Pile)

Max Activating Token Index: 693

Text #6

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3938. Min Act: -0.0000

Data Index: 1933638 (The Pile)

Max Activating Token Index: 933

Text #7

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1018299 (The Pile)

Max Activating Token Index: 845

Text #8

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3692. Min Act: -0.0000

Data Index: 678172 (The Pile)

Max Activating Token Index: 928

Text #9

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3426. Min Act: -0.0000

Data Index: 1748608 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3114. Min Act: -0.0000

Data Index: 1800972 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1215188 (The Pile)

Max Activating Token Index: 583

Text #12

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3956. Min Act: -0.0000

Data Index: 1920789 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1114198 (The Pile)

Max Activating Token Index: 453

Text #14

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3353. Min Act: -0.0000

Data Index: 677720 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2923. Min Act: -0.0000

Data Index: 511163 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.1421. Min Act: -0.0000

Data Index: 1932606 (The Pile)

Max Activating Token Index: 795

Text #17

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2497. Min Act: -0.0000

Data Index: 1017828 (The Pile)

Max Activating Token Index: 414

Text #18

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.3206. Min Act: -0.0000

Data Index: 1890243 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 1.6807. Min Range: -1.6807

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1063053 (The Pile)

Max Activating Token Index: 478