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

Dataset: The Pile

Neuron 3264 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: 1.9262. Min Range: -1.9262

Max Act: 1.9262. Min Act: -0.0000

Data Index: 581680 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.4161. Min Act: -0.0000

Data Index: 83026 (The Pile)

Max Activating Token Index: 372

Text #2

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.2553. Min Act: -0.0000

Data Index: 736739 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.1409. Min Act: -0.0000

Data Index: 1338987 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.1904. Min Act: -0.0000

Data Index: 212374 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.2389. Min Act: -0.0000

Data Index: 1377456 (The Pile)

Max Activating Token Index: 869

Text #6

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0853. Min Act: -0.0000

Data Index: 627379 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.1119. Min Act: -0.0000

Data Index: 1192521 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.2479. Min Act: -0.0000

Data Index: 1985855 (The Pile)

Max Activating Token Index: 402

Text #9

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.1308. Min Act: -0.0000

Data Index: 972956 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0800. Min Act: -0.0000

Data Index: 756893 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0674. Min Act: -0.0000

Data Index: 1451928 (The Pile)

Max Activating Token Index: 895

Text #12

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.1124. Min Act: -0.0000

Data Index: 1825978 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0786. Min Act: -0.0000

Data Index: 967804 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0881. Min Act: -0.0000

Data Index: 697994 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 1.9262. Min Range: -1.9262

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1576685 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0345. Min Act: -0.0000

Data Index: 1959405 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0327. Min Act: -0.0000

Data Index: 1261413 (The Pile)

Max Activating Token Index: 271

Text #18

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0659. Min Act: -0.0000

Data Index: 266454 (The Pile)

Max Activating Token Index: 201

Text #19

Max Range: 1.9262. Min Range: -1.9262

Max Act: 1.0857. Min Act: -0.0000

Data Index: 1669778 (The Pile)

Max Activating Token Index: 266