Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4515 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.7808. Min Act: -0.0002

Data Index: 605039 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.7593. Min Act: -0.0002

Data Index: 1254531 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.7250. Min Act: -0.0002

Data Index: 602864 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.7510. Min Act: -0.0002

Data Index: 829834 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.6578. Min Act: -0.0002

Data Index: 304004 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.4810. Min Act: -0.0002

Data Index: 1122037 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.5268. Min Act: -0.0002

Data Index: 1335180 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.5399. Min Act: -0.0002

Data Index: 905003 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.4507. Min Act: -0.0002

Data Index: 1127653 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.4488. Min Act: -0.0002

Data Index: 1313042 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.4349. Min Act: -0.0002

Data Index: 350026 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.4011. Min Act: -0.0002

Data Index: 897037 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.3991. Min Act: -0.0002

Data Index: 65500 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.3486. Min Act: -0.0002

Data Index: 1187334 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.3313. Min Act: -0.0002

Data Index: 485305 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.3447. Min Act: -0.0002

Data Index: 1167457 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.3261. Min Act: -0.0002

Data Index: 784911 (C4 (Web Text))

Max Activating Token Index: 541

Text #17

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.3108. Min Act: -0.0002

Data Index: 163110 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.2902. Min Act: -0.0002

Data Index: 1285159 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.7808. Min Range: -0.7808

Max Act: 0.2750. Min Act: -0.0002

Data Index: 557032 (C4 (Web Text))

Max Activating Token Index: 698