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

Dataset: The Pile

Neuron 1234 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: 0.0925. Min Range: -0.0925

Max Act: 0.0925. Min Act: -0.0000

Data Index: 953082 (The Pile)

Max Activating Token Index: 648

Text #1

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0719. Min Act: -0.0000

Data Index: 521201 (The Pile)

Max Activating Token Index: 513

Text #2

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0689. Min Act: -0.0000

Data Index: 200210 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0618. Min Act: -0.0000

Data Index: 663602 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1918338 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0603. Min Act: -0.0000

Data Index: 1322017 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1155857 (The Pile)

Max Activating Token Index: 444

Text #7

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1885317 (The Pile)

Max Activating Token Index: 413

Text #8

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0624. Min Act: -0.0000

Data Index: 75382 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1877276 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0562. Min Act: -0.0000

Data Index: 508945 (The Pile)

Max Activating Token Index: 576

Text #11

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0606. Min Act: -0.0000

Data Index: 741953 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1791818 (The Pile)

Max Activating Token Index: 67

Text #13

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0552. Min Act: -0.0000

Data Index: 286313 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1975190 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0493. Min Act: -0.0000

Data Index: 570216 (The Pile)

Max Activating Token Index: 888

Text #16

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1940636 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0476. Min Act: -0.0000

Data Index: 1960415 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0470. Min Act: -0.0000

Data Index: 1654031 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 0.0925. Min Range: -0.0925

Max Act: 0.0487. Min Act: -0.0000

Data Index: 21219 (The Pile)

Max Activating Token Index: 772