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

Dataset: The Pile

Neuron 2013 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: 1.3521. Min Range: -1.3521

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1638503 (The Pile)

Max Activating Token Index: 109

Text #1

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.3521. Min Act: -0.0000

Data Index: 901087 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1444056 (The Pile)

Max Activating Token Index: 651

Text #3

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1620226 (The Pile)

Max Activating Token Index: 260

Text #4

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0320. Min Act: -0.0000

Data Index: 824576 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9932. Min Act: -0.0000

Data Index: 883720 (The Pile)

Max Activating Token Index: 134

Text #6

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0426. Min Act: -0.0000

Data Index: 1587645 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1201804 (The Pile)

Max Activating Token Index: 915

Text #8

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0249. Min Act: -0.0000

Data Index: 308837 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9780. Min Act: -0.0000

Data Index: 1878420 (The Pile)

Max Activating Token Index: 381

Text #10

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9158. Min Act: -0.0000

Data Index: 706677 (The Pile)

Max Activating Token Index: 908

Text #11

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1476116 (The Pile)

Max Activating Token Index: 280

Text #12

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9309. Min Act: -0.0000

Data Index: 874173 (The Pile)

Max Activating Token Index: 393

Text #13

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1883220 (The Pile)

Max Activating Token Index: 793

Text #14

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9161. Min Act: -0.0000

Data Index: 487332 (The Pile)

Max Activating Token Index: 590

Text #15

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9129. Min Act: -0.0000

Data Index: 1446465 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 1.3521. Min Range: -1.3521

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1986297 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1613686 (The Pile)

Max Activating Token Index: 332

Text #18

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.8506. Min Act: -0.0000

Data Index: 801204 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 1.3521. Min Range: -1.3521

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1865977 (The Pile)

Max Activating Token Index: 222