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

Dataset: The Pile

Neuron 2890 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: 4.5701. Min Range: -4.5701

Max Act: 4.5701. Min Act: -0.0000

Data Index: 1686198 (The Pile)

Max Activating Token Index: 453

Text #1

Max Range: 4.5701. Min Range: -4.5701

Max Act: 4.0915. Min Act: -0.0000

Data Index: 1117759 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 4.5701. Min Range: -4.5701

Max Act: 4.3273. Min Act: -0.0000

Data Index: 47276 (The Pile)

Max Activating Token Index: 360

Text #3

Max Range: 4.5701. Min Range: -4.5701

Max Act: 4.1354. Min Act: -0.0000

Data Index: 693609 (The Pile)

Max Activating Token Index: 457

Text #4

Max Range: 4.5701. Min Range: -4.5701

Max Act: 4.1228. Min Act: -0.0000

Data Index: 266831 (The Pile)

Max Activating Token Index: 705

Text #5

Max Range: 4.5701. Min Range: -4.5701

Max Act: 4.0559. Min Act: -0.0000

Data Index: 718736 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.7444. Min Act: -0.0000

Data Index: 1942142 (The Pile)

Max Activating Token Index: 1010

Text #7

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.5440. Min Act: -0.0000

Data Index: 1363097 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.9629. Min Act: -0.0000

Data Index: 1587097 (The Pile)

Max Activating Token Index: 849

Text #9

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.7979. Min Act: -0.0000

Data Index: 914387 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.7747. Min Act: -0.0000

Data Index: 96119 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.4799. Min Act: -0.0000

Data Index: 613813 (The Pile)

Max Activating Token Index: 34

Text #12

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.7614. Min Act: -0.0000

Data Index: 812656 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.4004. Min Act: -0.0000

Data Index: 1120237 (The Pile)

Max Activating Token Index: 326

Text #14

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.4142. Min Act: -0.0000

Data Index: 259297 (The Pile)

Max Activating Token Index: 414

Text #15

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.3501. Min Act: -0.0000

Data Index: 508258 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.5161. Min Act: -0.0000

Data Index: 1131101 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.1536. Min Act: -0.0000

Data Index: 716506 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.3324. Min Act: -0.0000

Data Index: 266194 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 4.5701. Min Range: -4.5701

Max Act: 3.3035. Min Act: -0.0000

Data Index: 718500 (The Pile)

Max Activating Token Index: 66