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

Dataset: The Pile

Neuron 875 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.6330. Min Act: -0.0000

Data Index: 390060 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.4284. Min Act: -0.0000

Data Index: 1188423 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.3912. Min Act: -0.0000

Data Index: 136343 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1634099 (The Pile)

Max Activating Token Index: 365

Text #4

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9837. Min Act: -0.0000

Data Index: 290260 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.0838. Min Act: -0.0000

Data Index: 1305898 (The Pile)

Max Activating Token Index: 566

Text #6

Max Range: 1.6330. Min Range: -1.6330

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1716498 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9756. Min Act: -0.0000

Data Index: 1805407 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9559. Min Act: -0.0000

Data Index: 1315574 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9727. Min Act: -0.0000

Data Index: 694512 (The Pile)

Max Activating Token Index: 822

Text #10

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1149408 (The Pile)

Max Activating Token Index: 617

Text #11

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9528. Min Act: -0.0000

Data Index: 100976 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1101403 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1370654 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.8883. Min Act: -0.0000

Data Index: 304545 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.8153. Min Act: -0.0000

Data Index: 370667 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.8667. Min Act: -0.0000

Data Index: 253044 (The Pile)

Max Activating Token Index: 65

Text #17

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.8677. Min Act: -0.0000

Data Index: 567787 (The Pile)

Max Activating Token Index: 617

Text #18

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.8215. Min Act: -0.0000

Data Index: 1987442 (The Pile)

Max Activating Token Index: 946

Text #19

Max Range: 1.6330. Min Range: -1.6330

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1919832 (The Pile)

Max Activating Token Index: 121