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

Dataset: The Pile

Neuron 3335 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.5239. Min Act: -0.0000

Data Index: 472112 (The Pile)

Max Activating Token Index: 384

Text #1

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.5314. Min Act: -0.0000

Data Index: 1513218 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.4910. Min Act: -0.0000

Data Index: 1319805 (The Pile)

Max Activating Token Index: 949

Text #3

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.2768. Min Act: -0.0000

Data Index: 1352252 (The Pile)

Max Activating Token Index: 94

Text #4

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.3059. Min Act: -0.0000

Data Index: 1488857 (The Pile)

Max Activating Token Index: 695

Text #5

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.1586. Min Act: -0.0000

Data Index: 560344 (The Pile)

Max Activating Token Index: 197

Text #6

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.2755. Min Act: -0.0000

Data Index: 1784103 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.0984. Min Act: -0.0000

Data Index: 478730 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.1554. Min Act: -0.0000

Data Index: 292231 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.8514. Min Act: -0.0000

Data Index: 847585 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 3.5314. Min Range: -3.5314

Max Act: 3.1090. Min Act: -0.0000

Data Index: 1972599 (The Pile)

Max Activating Token Index: 902

Text #11

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.9328. Min Act: -0.0000

Data Index: 1502579 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.9217. Min Act: -0.0000

Data Index: 1000041 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.8373. Min Act: -0.0000

Data Index: 943415 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.8020. Min Act: -0.0000

Data Index: 486154 (The Pile)

Max Activating Token Index: 762

Text #15

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.8920. Min Act: -0.0000

Data Index: 173057 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.7821. Min Act: -0.0000

Data Index: 182568 (The Pile)

Max Activating Token Index: 464

Text #17

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.6362. Min Act: -0.0000

Data Index: 1132246 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.9870. Min Act: -0.0000

Data Index: 168811 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 3.5314. Min Range: -3.5314

Max Act: 2.5771. Min Act: -0.0000

Data Index: 700435 (The Pile)

Max Activating Token Index: 794