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

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

Neuron 1803 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.1600. Min Range: -2.1600

Max Act: 2.1600. Min Act: -0.0002

Data Index: 954481 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.8318. Min Act: -0.0002

Data Index: 597422 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.8066. Min Act: -0.0002

Data Index: 493926 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7890. Min Act: -0.0002

Data Index: 1082747 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.8479. Min Act: -0.0002

Data Index: 1238889 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7798. Min Act: -0.0003

Data Index: 501929 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7542. Min Act: -0.0002

Data Index: 681788 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7658. Min Act: -0.0002

Data Index: 871693 (C4 (Web Text))

Max Activating Token Index: 571

Text #8

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7040. Min Act: -0.0002

Data Index: 473853 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6703. Min Act: -0.0002

Data Index: 229995 (C4 (Web Text))

Max Activating Token Index: 621

Text #10

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6880. Min Act: -0.0002

Data Index: 1117135 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7254. Min Act: -0.0002

Data Index: 1295967 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7228. Min Act: -0.0002

Data Index: 1243054 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.7000. Min Act: -0.0002

Data Index: 686802 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6919. Min Act: -0.0002

Data Index: 994124 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6924. Min Act: -0.0002

Data Index: 633119 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6578. Min Act: -0.0002

Data Index: 1095845 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6414. Min Act: -0.0002

Data Index: 329219 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6425. Min Act: -0.0002

Data Index: 1312501 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 2.1600. Min Range: -2.1600

Max Act: 1.6482. Min Act: -0.0002

Data Index: 763617 (C4 (Web Text))

Max Activating Token Index: 610