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

Dataset: The Pile

Neuron 2749 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2341. Min Range: -3.2341

Max Act: 3.2341. Min Act: -0.0000

Data Index: 1752886 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 3.2341. Min Range: -3.2341

Max Act: 3.0023. Min Act: -0.0000

Data Index: 420323 (The Pile)

Max Activating Token Index: 211

Text #2

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.8610. Min Act: -0.0000

Data Index: 1497670 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 3.2341. Min Range: -3.2341

Max Act: 3.1227. Min Act: -0.0000

Data Index: 326604 (The Pile)

Max Activating Token Index: 314

Text #4

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.9217. Min Act: -0.0000

Data Index: 1233960 (The Pile)

Max Activating Token Index: 874

Text #5

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.8957. Min Act: -0.0000

Data Index: 1130513 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.7412. Min Act: -0.0000

Data Index: 1245688 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 3.2341. Min Range: -3.2341

Max Act: 3.0161. Min Act: -0.0000

Data Index: 52576 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.7086. Min Act: -0.0000

Data Index: 350426 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.9599. Min Act: -0.0000

Data Index: 1153848 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.8401. Min Act: -0.0000

Data Index: 764851 (The Pile)

Max Activating Token Index: 265

Text #11

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.5359. Min Act: -0.0000

Data Index: 288802 (The Pile)

Max Activating Token Index: 586

Text #12

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.9361. Min Act: -0.0000

Data Index: 1592834 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.6106. Min Act: -0.0000

Data Index: 1501857 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.7505. Min Act: -0.0000

Data Index: 540101 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.7279. Min Act: -0.0000

Data Index: 1058966 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.7213. Min Act: -0.0000

Data Index: 1101938 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.5776. Min Act: -0.0000

Data Index: 205179 (The Pile)

Max Activating Token Index: 558

Text #18

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.7091. Min Act: -0.0000

Data Index: 1180533 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 3.2341. Min Range: -3.2341

Max Act: 2.6773. Min Act: -0.0001

Data Index: 390716 (The Pile)

Max Activating Token Index: 680