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

Dataset: The Pile

Neuron 1712 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.8265. Min Act: -0.0000

Data Index: 251845 (The Pile)

Max Activating Token Index: 380

Text #1

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.4202. Min Act: -0.0000

Data Index: 861315 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.2806. Min Act: -0.0000

Data Index: 342368 (The Pile)

Max Activating Token Index: 452

Text #3

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0627. Min Act: -0.0000

Data Index: 832994 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1687294 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0543. Min Act: -0.0000

Data Index: 1329124 (The Pile)

Max Activating Token Index: 692

Text #6

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.1424. Min Act: -0.0000

Data Index: 1832180 (The Pile)

Max Activating Token Index: 372

Text #7

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.9676. Min Act: -0.0000

Data Index: 690116 (The Pile)

Max Activating Token Index: 442

Text #8

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8336. Min Act: -0.0000

Data Index: 4599 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 1.8265. Min Range: -1.8265

Max Act: 1.0084. Min Act: -0.0000

Data Index: 97639 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8284. Min Act: -0.0000

Data Index: 413314 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8351. Min Act: -0.0000

Data Index: 1593733 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8230. Min Act: -0.0000

Data Index: 1030027 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8697. Min Act: -0.0000

Data Index: 1783725 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8627. Min Act: -0.0000

Data Index: 1095465 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8173. Min Act: -0.0000

Data Index: 5536 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1764789 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1658256 (The Pile)

Max Activating Token Index: 627

Text #18

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8325. Min Act: -0.0000

Data Index: 350412 (The Pile)

Max Activating Token Index: 69

Text #19

Max Range: 1.8265. Min Range: -1.8265

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1981960 (The Pile)

Max Activating Token Index: 414