Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3149 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9292. Min Act: -0.0000

Data Index: 376409 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.9745. Min Act: -0.0000

Data Index: 888687 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8913. Min Act: -0.0000

Data Index: 1022061 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1298747 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8312. Min Act: -0.0000

Data Index: 1115553 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8441. Min Act: -0.0000

Data Index: 18611 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1049784 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8775. Min Act: -0.0000

Data Index: 254342 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8097. Min Act: -0.0000

Data Index: 633060 (C4 (Web Text))

Max Activating Token Index: 345

Text #9

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7815. Min Act: -0.0000

Data Index: 331269 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.8074. Min Act: -0.0000

Data Index: 536947 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7541. Min Act: -0.0000

Data Index: 669180 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1199111 (C4 (Web Text))

Max Activating Token Index: 397

Text #13

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7207. Min Act: -0.0000

Data Index: 308410 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1091167 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7524. Min Act: -0.0000

Data Index: 133968 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1059800 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7420. Min Act: -0.0000

Data Index: 633707 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.7183. Min Act: -0.0000

Data Index: 553584 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.9745. Min Range: -0.9745

Max Act: 0.6931. Min Act: -0.0000

Data Index: 1162348 (C4 (Web Text))

Max Activating Token Index: 608