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

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

Neuron 2704 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0615. Min Act: -0.0001

Data Index: 289499 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0573. Min Act: -0.0001

Data Index: 622721 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0562. Min Act: -0.0001

Data Index: 619290 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0531. Min Act: -0.0001

Data Index: 350884 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0522. Min Act: -0.0001

Data Index: 926449 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0439. Min Act: -0.0001

Data Index: 318800 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0475. Min Act: -0.0001

Data Index: 1032194 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1160225 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0449. Min Act: -0.0001

Data Index: 523848 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0453. Min Act: -0.0001

Data Index: 137156 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0441. Min Act: -0.0001

Data Index: 311376 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0460. Min Act: -0.0001

Data Index: 404973 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0417. Min Act: -0.0001

Data Index: 218589 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0384. Min Act: -0.0001

Data Index: 537597 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0397. Min Act: -0.0001

Data Index: 289346 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0390. Min Act: -0.0002

Data Index: 840810 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0388. Min Act: -0.0001

Data Index: 247085 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0385. Min Act: -0.0001

Data Index: 538430 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0394. Min Act: -0.0001

Data Index: 187835 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0615. Min Range: -0.0615

Max Act: 0.0394. Min Act: -0.0001

Data Index: 292532 (C4 (Web Text))

Max Activating Token Index: 905