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

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

Neuron 3423 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: 1.2937. Min Range: -1.2937

Max Act: 1.2721. Min Act: -0.0001

Data Index: 14742 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.2856. Min Act: -0.0001

Data Index: 229592 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.2937. Min Act: -0.0001

Data Index: 1238825 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.2211. Min Act: -0.0001

Data Index: 404312 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0968. Min Act: -0.0001

Data Index: 1146920 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.1028. Min Act: -0.0001

Data Index: 1231458 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.1012. Min Act: -0.0001

Data Index: 906704 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0575. Min Act: -0.0001

Data Index: 332827 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0813. Min Act: -0.0001

Data Index: 175767 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0227. Min Act: -0.0001

Data Index: 453125 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0409. Min Act: -0.0001

Data Index: 1039037 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 1.2937. Min Range: -1.2937

Max Act: 1.0726. Min Act: -0.0001

Data Index: 1107575 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9420. Min Act: -0.0001

Data Index: 1293071 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9915. Min Act: -0.0001

Data Index: 1055056 (C4 (Web Text))

Max Activating Token Index: 462

Text #14

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9499. Min Act: -0.0001

Data Index: 6580 (C4 (Web Text))

Max Activating Token Index: 572

Text #15

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9206. Min Act: -0.0001

Data Index: 745967 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8924. Min Act: -0.0001

Data Index: 764166 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.8636. Min Act: -0.0001

Data Index: 825008 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9352. Min Act: -0.0001

Data Index: 434040 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 1.2937. Min Range: -1.2937

Max Act: 0.9558. Min Act: -0.0001

Data Index: 685793 (C4 (Web Text))

Max Activating Token Index: 763