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

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

Neuron 1819 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1722. Min Range: -1.1722

Max Act: 1.1722. Min Act: -0.0000

Data Index: 1393610 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.8636. Min Act: -0.0000

Data Index: 664513 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.8868. Min Act: -0.0000

Data Index: 976489 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.8798. Min Act: -0.0000

Data Index: 642656 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.8713. Min Act: -0.0000

Data Index: 1007543 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.8574. Min Act: -0.0000

Data Index: 558891 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7876. Min Act: -0.0000

Data Index: 911169 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7870. Min Act: -0.0000

Data Index: 203448 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7577. Min Act: -0.0001

Data Index: 1532316 (Python Code)

Max Activating Token Index: 965

Text #9

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7090. Min Act: -0.0001

Data Index: 509208 (C4 (Web Text))

Max Activating Token Index: 442

Text #10

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7056. Min Act: -0.0000

Data Index: 871798 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7451. Min Act: -0.0001

Data Index: 1374876 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7035. Min Act: -0.0001

Data Index: 335684 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7152. Min Act: -0.0000

Data Index: 994949 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7093. Min Act: -0.0000

Data Index: 670567 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7291. Min Act: -0.0000

Data Index: 835657 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1290736 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.6933. Min Act: -0.0000

Data Index: 144596 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.7163. Min Act: -0.0000

Data Index: 765684 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.1722. Min Range: -1.1722

Max Act: 0.6909. Min Act: -0.0000

Data Index: 482203 (C4 (Web Text))

Max Activating Token Index: 220