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

Dataset: The Pile

Neuron 219 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1333328 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1320069 (The Pile)

Max Activating Token Index: 493

Text #2

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1572727 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0011. Min Act: -0.0000

Data Index: 797740 (The Pile)

Max Activating Token Index: 210

Text #4

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9911. Min Act: -0.0000

Data Index: 552716 (The Pile)

Max Activating Token Index: 248

Text #5

Max Range: 1.1126. Min Range: -1.1126

Max Act: 1.0740. Min Act: -0.0000

Data Index: 1855278 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9499. Min Act: -0.0000

Data Index: 1803747 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8931. Min Act: -0.0000

Data Index: 1739459 (The Pile)

Max Activating Token Index: 158

Text #8

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9272. Min Act: -0.0000

Data Index: 781802 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9558. Min Act: -0.0000

Data Index: 574778 (The Pile)

Max Activating Token Index: 734

Text #10

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9242. Min Act: -0.0000

Data Index: 971987 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8902. Min Act: -0.0000

Data Index: 1439423 (The Pile)

Max Activating Token Index: 236

Text #12

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1504764 (The Pile)

Max Activating Token Index: 131

Text #13

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1628072 (The Pile)

Max Activating Token Index: 399

Text #14

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9343. Min Act: -0.0000

Data Index: 229917 (The Pile)

Max Activating Token Index: 45

Text #15

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8999. Min Act: -0.0000

Data Index: 395976 (The Pile)

Max Activating Token Index: 748

Text #16

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9209. Min Act: -0.0000

Data Index: 993939 (The Pile)

Max Activating Token Index: 80

Text #17

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1320464 (The Pile)

Max Activating Token Index: 441

Text #18

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.9201. Min Act: -0.0000

Data Index: 305587 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 1.1126. Min Range: -1.1126

Max Act: 0.8821. Min Act: -0.0000

Data Index: 531570 (The Pile)

Max Activating Token Index: 269