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

Dataset: The Pile

Neuron 638 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: 0.3209. Min Range: -0.3209

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1592543 (The Pile)

Max Activating Token Index: 410

Text #1

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2770. Min Act: -0.0000

Data Index: 1489921 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1919032 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2531. Min Act: -0.0000

Data Index: 112780 (The Pile)

Max Activating Token Index: 425

Text #4

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1978546 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1635346 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2232. Min Act: -0.0000

Data Index: 1423846 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2219. Min Act: -0.0000

Data Index: 397597 (The Pile)

Max Activating Token Index: 905

Text #8

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2364. Min Act: -0.0000

Data Index: 158288 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1327535 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1161896 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.2069. Min Act: -0.0000

Data Index: 1286259 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1363584 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1936. Min Act: -0.0000

Data Index: 606521 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1858. Min Act: -0.0000

Data Index: 438884 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1955. Min Act: -0.0000

Data Index: 855420 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1794. Min Act: -0.0000

Data Index: 676515 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1356444 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1169540 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.3209. Min Range: -0.3209

Max Act: 0.1865. Min Act: -0.0000

Data Index: 496440 (The Pile)

Max Activating Token Index: 62