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

Dataset: The Pile

Neuron 2313 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 13.3321. Min Range: -13.3321

Max Act: 13.3321. Min Act: -0.0000

Data Index: 1879838 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.9743. Min Act: -0.0000

Data Index: 1103223 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.8879. Min Act: -0.0000

Data Index: 1907426 (The Pile)

Max Activating Token Index: 378

Text #3

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.9077. Min Act: -0.0000

Data Index: 1296860 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.8405. Min Act: -0.0000

Data Index: 1783863 (The Pile)

Max Activating Token Index: 300

Text #5

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.6917. Min Act: -0.0000

Data Index: 1192323 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.5967. Min Act: -0.0000

Data Index: 1707253 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.7874. Min Act: -0.0000

Data Index: 44562 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.7138. Min Act: -0.0000

Data Index: 289053 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.7876. Min Act: -0.0000

Data Index: 1689152 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.4495. Min Act: -0.0000

Data Index: 435432 (The Pile)

Max Activating Token Index: 525

Text #11

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.7745. Min Act: -0.0000

Data Index: 305983 (The Pile)

Max Activating Token Index: 133

Text #12

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.4311. Min Act: -0.0000

Data Index: 398212 (The Pile)

Max Activating Token Index: 178

Text #13

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.2563. Min Act: -0.0000

Data Index: 1554920 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.5375. Min Act: -0.0000

Data Index: 1506691 (The Pile)

Max Activating Token Index: 382

Text #15

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.5189. Min Act: -0.0000

Data Index: 356749 (The Pile)

Max Activating Token Index: 88

Text #16

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.3688. Min Act: -0.0000

Data Index: 47237 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.4438. Min Act: -0.0000

Data Index: 1084530 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.5286. Min Act: -0.0000

Data Index: 460321 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 13.3321. Min Range: -13.3321

Max Act: 12.4257. Min Act: -0.0000

Data Index: 96260 (The Pile)

Max Activating Token Index: 460