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

Dataset: The Pile

Neuron 3708 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: 1.2298. Min Range: -1.2298

Max Act: 1.2242. Min Act: -0.0000

Data Index: 215200 (The Pile)

Max Activating Token Index: 432

Text #1

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.1773. Min Act: -0.0000

Data Index: 1078256 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.1532. Min Act: -0.0000

Data Index: 607753 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.2298. Min Act: -0.0000

Data Index: 1761309 (The Pile)

Max Activating Token Index: 606

Text #4

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.0824. Min Act: -0.0000

Data Index: 1440428 (The Pile)

Max Activating Token Index: 879

Text #5

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.0278. Min Act: -0.0000

Data Index: 313439 (The Pile)

Max Activating Token Index: 180

Text #6

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1010293 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.1041. Min Act: -0.0000

Data Index: 826222 (The Pile)

Max Activating Token Index: 235

Text #8

Max Range: 1.2298. Min Range: -1.2298

Max Act: 1.0159. Min Act: -0.0000

Data Index: 474529 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.8950. Min Act: -0.0000

Data Index: 740752 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.9261. Min Act: -0.0000

Data Index: 914851 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1158574 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.8574. Min Act: -0.0000

Data Index: 124780 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1933696 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1704492 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1925738 (The Pile)

Max Activating Token Index: 331

Text #16

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.7884. Min Act: -0.0000

Data Index: 131654 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.7902. Min Act: -0.0000

Data Index: 1948664 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.8167. Min Act: -0.0000

Data Index: 1748225 (The Pile)

Max Activating Token Index: 996

Text #19

Max Range: 1.2298. Min Range: -1.2298

Max Act: 0.8624. Min Act: -0.0000

Data Index: 1261404 (The Pile)

Max Activating Token Index: 521