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

Dataset: The Pile

Neuron 2627 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: 1.0240. Min Range: -1.0240

Max Act: 1.0240. Min Act: -0.0000

Data Index: 1733196 (The Pile)

Max Activating Token Index: 226

Text #1

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.9333. Min Act: -0.0000

Data Index: 348813 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.8110. Min Act: -0.0000

Data Index: 215046 (The Pile)

Max Activating Token Index: 334

Text #3

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1739632 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7872. Min Act: -0.0000

Data Index: 1132306 (The Pile)

Max Activating Token Index: 13

Text #5

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7396. Min Act: -0.0000

Data Index: 1361543 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7869. Min Act: -0.0000

Data Index: 1024903 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7776. Min Act: -0.0000

Data Index: 181120 (The Pile)

Max Activating Token Index: 91

Text #8

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7694. Min Act: -0.0000

Data Index: 227484 (The Pile)

Max Activating Token Index: 385

Text #9

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1971778 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7131. Min Act: -0.0000

Data Index: 988667 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1756960 (The Pile)

Max Activating Token Index: 17

Text #12

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1415358 (The Pile)

Max Activating Token Index: 589

Text #13

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7032. Min Act: -0.0000

Data Index: 1817371 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1886605 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1457717 (The Pile)

Max Activating Token Index: 220

Text #16

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.6839. Min Act: -0.0000

Data Index: 498651 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1574209 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.7214. Min Act: -0.0000

Data Index: 387215 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 1.0240. Min Range: -1.0240

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1832426 (The Pile)

Max Activating Token Index: 28