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

Dataset: The Pile

Neuron 785 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.7426. Min Act: -0.0000

Data Index: 342045 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.7615. Min Act: -0.0000

Data Index: 953406 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6873. Min Act: -0.0000

Data Index: 801462 (The Pile)

Max Activating Token Index: 217

Text #3

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1024402 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1138527 (The Pile)

Max Activating Token Index: 302

Text #5

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5418. Min Act: -0.0000

Data Index: 612399 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1286143 (The Pile)

Max Activating Token Index: 786

Text #7

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5566. Min Act: -0.0000

Data Index: 882505 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1117151 (The Pile)

Max Activating Token Index: 675

Text #9

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5267. Min Act: -0.0000

Data Index: 936198 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1366311 (The Pile)

Max Activating Token Index: 414

Text #11

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1635244 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4965. Min Act: -0.0000

Data Index: 616640 (The Pile)

Max Activating Token Index: 616

Text #13

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1956563 (The Pile)

Max Activating Token Index: 458

Text #14

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.5024. Min Act: -0.0000

Data Index: 19501 (The Pile)

Max Activating Token Index: 356

Text #15

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1192089 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4617. Min Act: -0.0000

Data Index: 281804 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4356. Min Act: -0.0000

Data Index: 339670 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4158. Min Act: -0.0000

Data Index: 176938 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.7615. Min Range: -0.7615

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1122436 (The Pile)

Max Activating Token Index: 707