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

Dataset: The Pile

Neuron 1855 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: 0.7796. Min Range: -0.7796

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1957057 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1789908 (The Pile)

Max Activating Token Index: 207

Text #2

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7568. Min Act: -0.0000

Data Index: 1079714 (The Pile)

Max Activating Token Index: 675

Text #3

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7191. Min Act: -0.0000

Data Index: 169515 (The Pile)

Max Activating Token Index: 767

Text #4

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7401. Min Act: -0.0000

Data Index: 207867 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.6939. Min Act: -0.0000

Data Index: 1874968 (The Pile)

Max Activating Token Index: 574

Text #6

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7373. Min Act: -0.0000

Data Index: 1804871 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7245. Min Act: -0.0000

Data Index: 513312 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7272. Min Act: -0.0000

Data Index: 902234 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.6682. Min Act: -0.0000

Data Index: 1606159 (The Pile)

Max Activating Token Index: 409

Text #10

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7066. Min Act: -0.0000

Data Index: 15799 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.5629. Min Act: -0.0000

Data Index: 72244 (The Pile)

Max Activating Token Index: 740

Text #12

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7256. Min Act: -0.0000

Data Index: 678938 (The Pile)

Max Activating Token Index: 592

Text #13

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7132. Min Act: -0.0000

Data Index: 1112324 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1936531 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1762161 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7301. Min Act: -0.0000

Data Index: 966425 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7560. Min Act: -0.0000

Data Index: 721911 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1635500 (The Pile)

Max Activating Token Index: 279

Text #19

Max Range: 0.7796. Min Range: -0.7796

Max Act: 0.6794. Min Act: -0.0000

Data Index: 229508 (The Pile)

Max Activating Token Index: 542