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

Dataset: The Pile

Neuron 4078 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: 0.9045. Min Range: -0.9045

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1759848 (The Pile)

Max Activating Token Index: 877

Text #1

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.9045. Min Act: 0.0000

Data Index: 1464544 (The Pile)

Max Activating Token Index: 151

Text #2

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7997. Min Act: -0.0000

Data Index: 218507 (The Pile)

Max Activating Token Index: 570

Text #3

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7190. Min Act: -0.0000

Data Index: 825153 (The Pile)

Max Activating Token Index: 189

Text #4

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7424. Min Act: -0.0000

Data Index: 929930 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1709289 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.7160. Min Act: -0.0000

Data Index: 150381 (The Pile)

Max Activating Token Index: 597

Text #7

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6991. Min Act: -0.0000

Data Index: 1559072 (The Pile)

Max Activating Token Index: 764

Text #8

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6401. Min Act: -0.0000

Data Index: 679937 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6203. Min Act: -0.0000

Data Index: 167297 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1190769 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6088. Min Act: -0.0000

Data Index: 1814808 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6256. Min Act: -0.0000

Data Index: 1093141 (The Pile)

Max Activating Token Index: 809

Text #13

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6678. Min Act: -0.0000

Data Index: 91931 (The Pile)

Max Activating Token Index: 410

Text #14

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1263388 (The Pile)

Max Activating Token Index: 142

Text #15

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.5312. Min Act: -0.0000

Data Index: 1914342 (The Pile)

Max Activating Token Index: 691

Text #16

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6073. Min Act: -0.0000

Data Index: 1772802 (The Pile)

Max Activating Token Index: 381

Text #17

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1733345 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1749139 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 0.9045. Min Range: -0.9045

Max Act: 0.6131. Min Act: -0.0000

Data Index: 581647 (The Pile)

Max Activating Token Index: 751