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

Dataset: The Pile

Neuron 2210 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: 0.6323. Min Range: -0.6323

Max Act: 0.6089. Min Act: -0.0000

Data Index: 838171 (The Pile)

Max Activating Token Index: 889

Text #1

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1393149 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.6094. Min Act: -0.0000

Data Index: 542273 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1579321 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5946. Min Act: -0.0000

Data Index: 648643 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1728363 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5641. Min Act: -0.0000

Data Index: 766315 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5195. Min Act: -0.0000

Data Index: 559554 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5763. Min Act: -0.0000

Data Index: 619295 (The Pile)

Max Activating Token Index: 263

Text #9

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1884588 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5429. Min Act: -0.0000

Data Index: 896416 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4478. Min Act: -0.0000

Data Index: 148891 (The Pile)

Max Activating Token Index: 697

Text #12

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5327. Min Act: -0.0000

Data Index: 674795 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4838. Min Act: -0.0000

Data Index: 648838 (The Pile)

Max Activating Token Index: 28

Text #14

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1636126 (The Pile)

Max Activating Token Index: 860

Text #15

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1266059 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4776. Min Act: -0.0000

Data Index: 172791 (The Pile)

Max Activating Token Index: 133

Text #17

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4751. Min Act: -0.0000

Data Index: 197909 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4019. Min Act: -0.0000

Data Index: 915282 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 0.6323. Min Range: -0.6323

Max Act: 0.4672. Min Act: -0.0000

Data Index: 200612 (The Pile)

Max Activating Token Index: 891