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

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

Neuron 996 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.3565. Min Act: -0.0001

Data Index: 353828 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.3536. Min Act: -0.0001

Data Index: 92816 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2903. Min Act: -0.0001

Data Index: 290090 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2836. Min Act: -0.0001

Data Index: 1129510 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2685. Min Act: -0.0001

Data Index: 193266 (C4 (Web Text))

Max Activating Token Index: 526

Text #5

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2867. Min Act: -0.0001

Data Index: 589730 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2850. Min Act: -0.0001

Data Index: 646953 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2628. Min Act: -0.0001

Data Index: 779516 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.3077. Min Act: -0.0001

Data Index: 1157778 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2575. Min Act: -0.0001

Data Index: 202003 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2673. Min Act: -0.0001

Data Index: 144983 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2730. Min Act: -0.0001

Data Index: 633804 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2724. Min Act: -0.0001

Data Index: 1164648 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2612. Min Act: -0.0001

Data Index: 975926 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2596. Min Act: -0.0001

Data Index: 157843 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2571. Min Act: -0.0001

Data Index: 333999 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2655. Min Act: -0.0001

Data Index: 894705 (C4 (Web Text))

Max Activating Token Index: 519

Text #17

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2567. Min Act: -0.0001

Data Index: 254243 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2456. Min Act: -0.0001

Data Index: 567932 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.3565. Min Range: -0.3565

Max Act: 0.2529. Min Act: -0.0001

Data Index: 761728 (C4 (Web Text))

Max Activating Token Index: 18