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

Dataset: The Pile

Neuron 1937 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.3725. Min Act: -0.0000

Data Index: 1549837 (The Pile)

Max Activating Token Index: 470

Text #1

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1734021 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0439. Min Act: -0.0000

Data Index: 364825 (The Pile)

Max Activating Token Index: 475

Text #3

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0825. Min Act: -0.0000

Data Index: 1199383 (The Pile)

Max Activating Token Index: 720

Text #4

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9849. Min Act: -0.0000

Data Index: 783402 (The Pile)

Max Activating Token Index: 786

Text #5

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0092. Min Act: -0.0000

Data Index: 18484 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8987. Min Act: -0.0000

Data Index: 231535 (The Pile)

Max Activating Token Index: 394

Text #7

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9401. Min Act: -0.0000

Data Index: 660586 (The Pile)

Max Activating Token Index: 513

Text #8

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9813. Min Act: -0.0000

Data Index: 252997 (The Pile)

Max Activating Token Index: 985

Text #9

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9709. Min Act: -0.0000

Data Index: 775695 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8934. Min Act: -0.0000

Data Index: 170442 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1560881 (The Pile)

Max Activating Token Index: 591

Text #12

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1095115 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8519. Min Act: -0.0000

Data Index: 472243 (The Pile)

Max Activating Token Index: 855

Text #14

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8363. Min Act: -0.0000

Data Index: 429176 (The Pile)

Max Activating Token Index: 310

Text #15

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8341. Min Act: -0.0000

Data Index: 379887 (The Pile)

Max Activating Token Index: 546

Text #16

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1818261 (The Pile)

Max Activating Token Index: 214

Text #17

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8726. Min Act: -0.0000

Data Index: 427072 (The Pile)

Max Activating Token Index: 940

Text #18

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1666492 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1957038 (The Pile)

Max Activating Token Index: 626