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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1666 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1575. Min Act: -0.0003

Data Index: 1086415 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.1219. Min Act: -0.0003

Data Index: 314513 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0506. Min Act: -0.0003

Data Index: 150372 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0087. Min Act: -0.0003

Data Index: 247957 (C4 (Web Text))

Max Activating Token Index: 652

Text #4

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9167. Min Act: -0.0003

Data Index: 34144 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9416. Min Act: -0.0003

Data Index: 403320 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0110. Min Act: -0.0003

Data Index: 1257309 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0101. Min Act: -0.0003

Data Index: 459280 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0353. Min Act: -0.0003

Data Index: 1147667 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9856. Min Act: -0.0003

Data Index: 1029989 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0021. Min Act: -0.0003

Data Index: 998183 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0869. Min Act: -0.0003

Data Index: 849871 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0578. Min Act: -0.0003

Data Index: 950189 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0216. Min Act: -0.0003

Data Index: 43226 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9351. Min Act: -0.0003

Data Index: 384347 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9047. Min Act: -0.0003

Data Index: 1000931 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0702. Min Act: -0.0003

Data Index: 160021 (C4 (Web Text))

Max Activating Token Index: 340

Text #17

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9781. Min Act: -0.0003

Data Index: 344122 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 1.1575. Min Range: -1.1575

Max Act: 0.9118. Min Act: -0.0003

Data Index: 271756 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 1.1575. Min Range: -1.1575

Max Act: 1.0283. Min Act: -0.0003

Data Index: 575546 (C4 (Web Text))

Max Activating Token Index: 161