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

Dataset: The Pile

Neuron 2143 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: 0.6955. Min Range: -0.6955

Max Act: 0.6955. Min Act: -0.0000

Data Index: 387240 (The Pile)

Max Activating Token Index: 784

Text #1

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1379221 (The Pile)

Max Activating Token Index: 676

Text #2

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5539. Min Act: -0.0000

Data Index: 726880 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1802628 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1534725 (The Pile)

Max Activating Token Index: 171

Text #5

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5490. Min Act: -0.0000

Data Index: 315752 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1436676 (The Pile)

Max Activating Token Index: 589

Text #7

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1898241 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1880293 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5849. Min Act: -0.0000

Data Index: 381792 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1746151 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1777245 (The Pile)

Max Activating Token Index: 46

Text #12

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5276. Min Act: -0.0000

Data Index: 1747271 (The Pile)

Max Activating Token Index: 257

Text #13

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1471485 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4444. Min Act: -0.0000

Data Index: 1976381 (The Pile)

Max Activating Token Index: 36

Text #15

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.5085. Min Act: -0.0000

Data Index: 867565 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4918. Min Act: -0.0000

Data Index: 354171 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4923. Min Act: -0.0000

Data Index: 792611 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4831. Min Act: -0.0000

Data Index: 472259 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 0.6955. Min Range: -0.6955

Max Act: 0.4788. Min Act: -0.0000

Data Index: 423318 (The Pile)

Max Activating Token Index: 210