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

Dataset: The Pile

Neuron 158 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.5253. Min Act: -0.0000

Data Index: 988175 (The Pile)

Max Activating Token Index: 186

Text #1

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4912. Min Act: -0.0000

Data Index: 1434179 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4461. Min Act: -0.0000

Data Index: 579348 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4419. Min Act: -0.0000

Data Index: 789585 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4246. Min Act: -0.0000

Data Index: 1754306 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1721560 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1059472 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4250. Min Act: -0.0000

Data Index: 398158 (The Pile)

Max Activating Token Index: 74

Text #8

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1113265 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1117860 (The Pile)

Max Activating Token Index: 876

Text #10

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4273. Min Act: -0.0000

Data Index: 664954 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4090. Min Act: -0.0000

Data Index: 1115971 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1844821 (The Pile)

Max Activating Token Index: 962

Text #13

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4053. Min Act: -0.0000

Data Index: 287694 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4124. Min Act: -0.0000

Data Index: 1502297 (The Pile)

Max Activating Token Index: 1005

Text #15

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1769607 (The Pile)

Max Activating Token Index: 695

Text #16

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3852. Min Act: -0.0000

Data Index: 455497 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4028. Min Act: -0.0000

Data Index: 856933 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.4259. Min Act: -0.0000

Data Index: 370893 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 0.5253. Min Range: -0.5253

Max Act: 0.3942. Min Act: -0.0000

Data Index: 896154 (The Pile)

Max Activating Token Index: 503