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

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

Neuron 681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1009. Min Act: -0.0001

Data Index: 675534 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.1062. Min Act: -0.0001

Data Index: 1093369 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0938. Min Act: -0.0001

Data Index: 891957 (C4 (Web Text))

Max Activating Token Index: 276

Text #3

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0957. Min Act: -0.0001

Data Index: 788948 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0968. Min Act: -0.0001

Data Index: 847381 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0848. Min Act: -0.0001

Data Index: 975177 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0912. Min Act: -0.0001

Data Index: 480624 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0787. Min Act: -0.0001

Data Index: 392558 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0833. Min Act: -0.0001

Data Index: 148529 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0876. Min Act: -0.0001

Data Index: 704523 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0784. Min Act: -0.0001

Data Index: 750758 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0759. Min Act: -0.0001

Data Index: 541298 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0766. Min Act: -0.0001

Data Index: 34906 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0736. Min Act: -0.0001

Data Index: 824728 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1173465 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0779. Min Act: -0.0001

Data Index: 723950 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0748. Min Act: -0.0001

Data Index: 301765 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0775. Min Act: -0.0001

Data Index: 630509 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0745. Min Act: -0.0001

Data Index: 752940 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.1062. Min Range: -0.1062

Max Act: 0.0715. Min Act: -0.0001

Data Index: 987788 (C4 (Web Text))

Max Activating Token Index: 410