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

Dataset: The Pile

Neuron 333 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: 1.0184. Min Range: -1.0184

Max Act: 0.9943. Min Act: -0.0000

Data Index: 1934876 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 1.0184. Min Range: -1.0184

Max Act: 1.0184. Min Act: -0.0000

Data Index: 173993 (The Pile)

Max Activating Token Index: 440

Text #2

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9135. Min Act: -0.0000

Data Index: 942868 (The Pile)

Max Activating Token Index: 144

Text #3

Max Range: 1.0184. Min Range: -1.0184

Max Act: 1.0162. Min Act: -0.0000

Data Index: 1501898 (The Pile)

Max Activating Token Index: 887

Text #4

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1401274 (The Pile)

Max Activating Token Index: 944

Text #5

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1886678 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7926. Min Act: -0.0000

Data Index: 802976 (The Pile)

Max Activating Token Index: 274

Text #7

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9021. Min Act: -0.0000

Data Index: 1733283 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1193319 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8524. Min Act: -0.0000

Data Index: 149777 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1127179 (The Pile)

Max Activating Token Index: 323

Text #11

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1654053 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1792212 (The Pile)

Max Activating Token Index: 670

Text #13

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1384430 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.7956. Min Act: -0.0000

Data Index: 532064 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8110. Min Act: -0.0000

Data Index: 798299 (The Pile)

Max Activating Token Index: 357

Text #16

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8023. Min Act: -0.0000

Data Index: 221964 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1741466 (The Pile)

Max Activating Token Index: 369

Text #18

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8689. Min Act: -0.0000

Data Index: 1017208 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 1.0184. Min Range: -1.0184

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1197754 (The Pile)

Max Activating Token Index: 820