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

Dataset: The Pile

Neuron 4385 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5346. Min Range: -2.5346

Max Act: 2.2699. Min Act: -0.0000

Data Index: 1217286 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 2.5346. Min Range: -2.5346

Max Act: 2.5346. Min Act: -0.0000

Data Index: 1213610 (The Pile)

Max Activating Token Index: 519

Text #2

Max Range: 2.5346. Min Range: -2.5346

Max Act: 2.0316. Min Act: -0.0000

Data Index: 331367 (The Pile)

Max Activating Token Index: 128

Text #3

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.9864. Min Act: -0.0000

Data Index: 1051567 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.9457. Min Act: -0.0000

Data Index: 1347119 (The Pile)

Max Activating Token Index: 244

Text #5

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.8603. Min Act: -0.0000

Data Index: 642222 (The Pile)

Max Activating Token Index: 67

Text #6

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.5657. Min Act: -0.0000

Data Index: 466593 (The Pile)

Max Activating Token Index: 513

Text #7

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.8079. Min Act: -0.0000

Data Index: 197052 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.7051. Min Act: -0.0000

Data Index: 1159335 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.6746. Min Act: -0.0000

Data Index: 235871 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1097230 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.5081. Min Act: -0.0000

Data Index: 182858 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.5461. Min Act: -0.0000

Data Index: 1702734 (The Pile)

Max Activating Token Index: 387

Text #13

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.2156. Min Act: -0.0000

Data Index: 1513229 (The Pile)

Max Activating Token Index: 915

Text #14

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1379879 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.4159. Min Act: -0.0000

Data Index: 776863 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.3540. Min Act: -0.0000

Data Index: 1473950 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.4249. Min Act: -0.0000

Data Index: 206482 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.3660. Min Act: -0.0000

Data Index: 234468 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 2.5346. Min Range: -2.5346

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1727289 (The Pile)

Max Activating Token Index: 98