Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3361 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.7084. Min Act: -0.0000

Data Index: 1952974 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.7177. Min Act: -0.0000

Data Index: 274164 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.6862. Min Act: -0.0000

Data Index: 1478608 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1381325 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.5501. Min Act: -0.0000

Data Index: 1209902 (The Pile)

Max Activating Token Index: 437

Text #5

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.6093. Min Act: 0.0000

Data Index: 59999 (The Pile)

Max Activating Token Index: 476

Text #6

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.3396. Min Act: 0.0000

Data Index: 347525 (The Pile)

Max Activating Token Index: 263

Text #7

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1658. Min Act: -0.0000

Data Index: 16809 (The Pile)

Max Activating Token Index: 780

Text #8

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1717. Min Act: -0.0000

Data Index: 757917 (The Pile)

Max Activating Token Index: 58

Text #9

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1887. Min Act: -0.0000

Data Index: 171425 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1677159 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1993. Min Act: -0.0000

Data Index: 528056 (The Pile)

Max Activating Token Index: 342

Text #12

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1411818 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1668. Min Act: -0.0000

Data Index: 155959 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1671. Min Act: -0.0000

Data Index: 259228 (The Pile)

Max Activating Token Index: 239

Text #15

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1483. Min Act: -0.0000

Data Index: 1946179 (The Pile)

Max Activating Token Index: 327

Text #16

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1331. Min Act: -0.0000

Data Index: 337199 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1148. Min Act: 0.0000

Data Index: 377249 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.1035. Min Act: 0.0000

Data Index: 316978 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 1.7177. Min Range: -1.7177

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1170366 (The Pile)

Max Activating Token Index: 699