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

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

Neuron 3610 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: 0.5924. Min Range: -0.5924

Max Act: 0.5924. Min Act: -0.0001

Data Index: 497052 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5425. Min Act: -0.0001

Data Index: 945516 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5353. Min Act: -0.0001

Data Index: 248937 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4992. Min Act: -0.0001

Data Index: 447620 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4833. Min Act: -0.0001

Data Index: 892534 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5136. Min Act: -0.0001

Data Index: 1149338 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5113. Min Act: -0.0001

Data Index: 656211 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5122. Min Act: -0.0001

Data Index: 651969 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4979. Min Act: -0.0001

Data Index: 282597 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4996. Min Act: -0.0001

Data Index: 1277927 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5154. Min Act: -0.0001

Data Index: 408605 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4947. Min Act: -0.0001

Data Index: 946253 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4709. Min Act: -0.0001

Data Index: 889347 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4695. Min Act: -0.0001

Data Index: 43900 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.5053. Min Act: -0.0001

Data Index: 694477 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4684. Min Act: -0.0001

Data Index: 430972 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4847. Min Act: -0.0001

Data Index: 765680 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4783. Min Act: -0.0001

Data Index: 1222532 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4648. Min Act: -0.0001

Data Index: 826303 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.5924. Min Range: -0.5924

Max Act: 0.4728. Min Act: -0.0001

Data Index: 307905 (C4 (Web Text))

Max Activating Token Index: 703