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

Dataset: The Pile

Neuron 2252 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0000

Data Index: 1127886 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0469. Min Act: -0.0000

Data Index: 1956782 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0447. Min Act: -0.0000

Data Index: 826484 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0418. Min Act: -0.0000

Data Index: 697113 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0404. Min Act: -0.0000

Data Index: 171045 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0404. Min Act: -0.0000

Data Index: 731895 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0389. Min Act: -0.0000

Data Index: 447955 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0388. Min Act: -0.0000

Data Index: 1544965 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1015355 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0373. Min Act: -0.0000

Data Index: 713058 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1245614 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1447704 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0342. Min Act: -0.0000

Data Index: 1725769 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0354. Min Act: -0.0000

Data Index: 920723 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0351. Min Act: -0.0000

Data Index: 1347570 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1724276 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0343. Min Act: -0.0000

Data Index: 560884 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0341. Min Act: -0.0000

Data Index: 472030 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0341. Min Act: -0.0000

Data Index: 289716 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0340. Min Act: -0.0000

Data Index: 650436 (The Pile)

Max Activating Token Index: 1023