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

Dataset: The Pile

Neuron 4938 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8124. Min Act: -0.0000

Data Index: 13363 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.9361. Min Act: -0.0000

Data Index: 249801 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8108. Min Act: -0.0000

Data Index: 449386 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8379. Min Act: -0.0000

Data Index: 419273 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1752841 (The Pile)

Max Activating Token Index: 757

Text #5

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1158344 (The Pile)

Max Activating Token Index: 314

Text #6

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1678726 (The Pile)

Max Activating Token Index: 936

Text #7

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.7601. Min Act: -0.0000

Data Index: 258286 (The Pile)

Max Activating Token Index: 345

Text #8

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1336431 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1123705 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.6603. Min Act: -0.0000

Data Index: 963863 (The Pile)

Max Activating Token Index: 1017

Text #11

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.7876. Min Act: -0.0000

Data Index: 653624 (The Pile)

Max Activating Token Index: 385

Text #12

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.8302. Min Act: -0.0000

Data Index: 572659 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.7795. Min Act: -0.0000

Data Index: 1965286 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.6235. Min Act: -0.0000

Data Index: 186091 (The Pile)

Max Activating Token Index: 710

Text #15

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.7075. Min Act: -0.0000

Data Index: 902505 (The Pile)

Max Activating Token Index: 416

Text #16

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.7385. Min Act: -0.0000

Data Index: 687426 (The Pile)

Max Activating Token Index: 243

Text #17

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.7173. Min Act: -0.0000

Data Index: 603573 (The Pile)

Max Activating Token Index: 284

Text #18

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.6415. Min Act: -0.0000

Data Index: 518451 (The Pile)

Max Activating Token Index: 107

Text #19

Max Range: 0.9361. Min Range: -0.9361

Max Act: 0.6675. Min Act: -0.0000

Data Index: 948574 (The Pile)

Max Activating Token Index: 146