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

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

Neuron 745 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.9700. Min Act: -0.0002

Data Index: 916750 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.9119. Min Act: -0.0002

Data Index: 1204286 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.9176. Min Act: -0.0002

Data Index: 974032 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.8632. Min Act: -0.0002

Data Index: 877837 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.6177. Min Act: -0.0001

Data Index: 1192253 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.6403. Min Act: -0.0001

Data Index: 512247 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.8064. Min Act: -0.0002

Data Index: 126188 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.6416. Min Act: -0.0002

Data Index: 286977 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.6888. Min Act: -0.0001

Data Index: 341017 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.4723. Min Act: -0.0002

Data Index: 6504 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.5090. Min Act: -0.0001

Data Index: 982107 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.5746. Min Act: -0.0002

Data Index: 183596 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.5539. Min Act: -0.0001

Data Index: 13946 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.5829. Min Act: -0.0002

Data Index: 707748 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.4647. Min Act: -0.0001

Data Index: 765897 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.2904. Min Act: -0.0001

Data Index: 630888 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.4258. Min Act: -0.0002

Data Index: 479797 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.4299. Min Act: -0.0002

Data Index: 480973 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.4429. Min Act: -0.0001

Data Index: 1293890 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 1.9700. Min Range: -1.9700

Max Act: 1.3675. Min Act: -0.0001

Data Index: 926960 (C4 (Web Text))

Max Activating Token Index: 752