Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1174 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.8610. Min Act: -0.0000

Data Index: 566872 (The Pile)

Max Activating Token Index: 809

Text #1

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.8706. Min Act: -0.0000

Data Index: 1087276 (The Pile)

Max Activating Token Index: 723

Text #2

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.7495. Min Act: -0.0000

Data Index: 1959675 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.7296. Min Act: -0.0000

Data Index: 960006 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.7385. Min Act: -0.0000

Data Index: 779034 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.6994. Min Act: -0.0000

Data Index: 414569 (The Pile)

Max Activating Token Index: 612

Text #6

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.6731. Min Act: -0.0000

Data Index: 862425 (The Pile)

Max Activating Token Index: 346

Text #7

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.5790. Min Act: -0.0000

Data Index: 1865430 (The Pile)

Max Activating Token Index: 309

Text #8

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.6708. Min Act: -0.0000

Data Index: 386110 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.5735. Min Act: -0.0000

Data Index: 315854 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.5469. Min Act: -0.0000

Data Index: 415906 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.6433. Min Act: -0.0000

Data Index: 1272233 (The Pile)

Max Activating Token Index: 63

Text #12

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.5350. Min Act: -0.0000

Data Index: 441128 (The Pile)

Max Activating Token Index: 104

Text #13

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.7136. Min Act: -0.0000

Data Index: 141682 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.5720. Min Act: -0.0000

Data Index: 1800833 (The Pile)

Max Activating Token Index: 161

Text #15

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1629483 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.4220. Min Act: -0.0000

Data Index: 1886205 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.4620. Min Act: -0.0000

Data Index: 610230 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.5859. Min Act: -0.0000

Data Index: 948722 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 1.8706. Min Range: -1.8706

Max Act: 1.4906. Min Act: -0.0000

Data Index: 783034 (The Pile)

Max Activating Token Index: 468