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

Dataset: The Pile

Neuron 1975 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: 0.3836. Min Range: -0.3836

Max Act: 0.3836. Min Act: -0.0000

Data Index: 269134 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1746656 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3351. Min Act: -0.0000

Data Index: 100817 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1987108 (The Pile)

Max Activating Token Index: 578

Text #4

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3175. Min Act: -0.0000

Data Index: 633981 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3397. Min Act: -0.0000

Data Index: 707636 (The Pile)

Max Activating Token Index: 454

Text #6

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1112827 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1541411 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3110. Min Act: -0.0000

Data Index: 1347283 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1814775 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3196. Min Act: -0.0000

Data Index: 549050 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1073536 (The Pile)

Max Activating Token Index: 850

Text #12

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1502312 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2962. Min Act: -0.0000

Data Index: 798066 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2788. Min Act: -0.0000

Data Index: 535968 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2912. Min Act: -0.0000

Data Index: 471237 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3206. Min Act: -0.0000

Data Index: 474965 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2938. Min Act: -0.0000

Data Index: 753469 (The Pile)

Max Activating Token Index: 601

Text #18

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1954150 (The Pile)

Max Activating Token Index: 323

Text #19

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2531. Min Act: -0.0000

Data Index: 1820813 (The Pile)

Max Activating Token Index: 585