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

Dataset: The Pile

Neuron 1185 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: 1.1747. Min Range: -1.1747

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1792431 (The Pile)

Max Activating Token Index: 973

Text #1

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.1747. Min Act: -0.0000

Data Index: 569915 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.1738. Min Act: -0.0000

Data Index: 1511121 (The Pile)

Max Activating Token Index: 450

Text #3

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1741257 (The Pile)

Max Activating Token Index: 200

Text #4

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0961. Min Act: -0.0000

Data Index: 866443 (The Pile)

Max Activating Token Index: 335

Text #5

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0348. Min Act: -0.0000

Data Index: 1136186 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1698246 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9810. Min Act: -0.0000

Data Index: 378098 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0712. Min Act: -0.0000

Data Index: 310602 (The Pile)

Max Activating Token Index: 57

Text #9

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0440. Min Act: -0.0000

Data Index: 1816489 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0155. Min Act: -0.0000

Data Index: 939138 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0286. Min Act: -0.0000

Data Index: 626166 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9339. Min Act: -0.0000

Data Index: 1850505 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9961. Min Act: -0.0000

Data Index: 205631 (The Pile)

Max Activating Token Index: 96

Text #14

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9807. Min Act: -0.0000

Data Index: 947671 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0114. Min Act: -0.0000

Data Index: 853128 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1463784 (The Pile)

Max Activating Token Index: 203

Text #17

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1400736 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 1.1747. Min Range: -1.1747

Max Act: 1.0260. Min Act: -0.0000

Data Index: 802343 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 1.1747. Min Range: -1.1747

Max Act: 0.9855. Min Act: -0.0000

Data Index: 730444 (The Pile)

Max Activating Token Index: 485