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

Dataset: The Pile

Neuron 4023 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.8252. Min Act: -0.0000

Data Index: 1516157 (The Pile)

Max Activating Token Index: 494

Text #1

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.7818. Min Act: -0.0000

Data Index: 1121612 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.7376. Min Act: -0.0000

Data Index: 1743099 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.7218. Min Act: -0.0000

Data Index: 759254 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.6991. Min Act: -0.0000

Data Index: 301146 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.4683. Min Act: -0.0000

Data Index: 409161 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.5516. Min Act: -0.0000

Data Index: 253126 (The Pile)

Max Activating Token Index: 1014

Text #7

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.6053. Min Act: -0.0000

Data Index: 1774093 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.4590. Min Act: -0.0000

Data Index: 434805 (The Pile)

Max Activating Token Index: 941

Text #9

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.3804. Min Act: -0.0000

Data Index: 1028687 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.4614. Min Act: -0.0000

Data Index: 1454757 (The Pile)

Max Activating Token Index: 422

Text #11

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.3762. Min Act: -0.0000

Data Index: 418755 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.5450. Min Act: -0.0000

Data Index: 1333910 (The Pile)

Max Activating Token Index: 347

Text #13

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.4460. Min Act: -0.0000

Data Index: 1833586 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.2635. Min Act: -0.0000

Data Index: 1228410 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.4273. Min Act: -0.0000

Data Index: 724950 (The Pile)

Max Activating Token Index: 369

Text #16

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.3286. Min Act: -0.0000

Data Index: 402452 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.3221. Min Act: -0.0000

Data Index: 377497 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.3932. Min Act: -0.0000

Data Index: 101914 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 1.8252. Min Range: -1.8252

Max Act: 1.3049. Min Act: -0.0000

Data Index: 532030 (The Pile)

Max Activating Token Index: 188