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

Dataset: The Pile

Neuron 2423 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: 1.7358. Min Range: -1.7358

Max Act: 1.7358. Min Act: -0.0000

Data Index: 1953537 (The Pile)

Max Activating Token Index: 840

Text #1

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5529. Min Act: -0.0000

Data Index: 974417 (The Pile)

Max Activating Token Index: 975

Text #2

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5405. Min Act: -0.0000

Data Index: 882243 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5509. Min Act: -0.0000

Data Index: 1407677 (The Pile)

Max Activating Token Index: 43

Text #4

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.4535. Min Act: -0.0000

Data Index: 920943 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.4212. Min Act: -0.0000

Data Index: 1144564 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.5039. Min Act: -0.0000

Data Index: 870194 (The Pile)

Max Activating Token Index: 640

Text #7

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2544. Min Act: -0.0000

Data Index: 359962 (The Pile)

Max Activating Token Index: 890

Text #8

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2499. Min Act: -0.0000

Data Index: 450776 (The Pile)

Max Activating Token Index: 156

Text #9

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.3210. Min Act: -0.0000

Data Index: 1436612 (The Pile)

Max Activating Token Index: 121

Text #10

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2274. Min Act: -0.0000

Data Index: 1876118 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2776. Min Act: -0.0000

Data Index: 929647 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2700. Min Act: -0.0000

Data Index: 645063 (The Pile)

Max Activating Token Index: 852

Text #13

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2402. Min Act: -0.0000

Data Index: 1792215 (The Pile)

Max Activating Token Index: 859

Text #14

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2113. Min Act: -0.0000

Data Index: 259834 (The Pile)

Max Activating Token Index: 901

Text #15

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.1743. Min Act: -0.0000

Data Index: 723065 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.1338. Min Act: -0.0000

Data Index: 698720 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.1603. Min Act: -0.0000

Data Index: 395433 (The Pile)

Max Activating Token Index: 977

Text #18

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1923041 (The Pile)

Max Activating Token Index: 1006

Text #19

Max Range: 1.7358. Min Range: -1.7358

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1091541 (The Pile)

Max Activating Token Index: 824