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

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

Neuron 2205 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0002

Data Index: 825504 (C4 (Web Text))

Max Activating Token Index: 452

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0497. Min Act: -0.0002

Data Index: 692167 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0489. Min Act: -0.0002

Data Index: 790880 (C4 (Web Text))

Max Activating Token Index: 303

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0446. Min Act: -0.0002

Data Index: 490943 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1232826 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0420. Min Act: -0.0002

Data Index: 638745 (C4 (Web Text))

Max Activating Token Index: 79

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0411. Min Act: -0.0002

Data Index: 207274 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0400. Min Act: -0.0002

Data Index: 112844 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0396. Min Act: -0.0002

Data Index: 550651 (C4 (Web Text))

Max Activating Token Index: 624

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0397. Min Act: -0.0002

Data Index: 397756 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0392. Min Act: -0.0002

Data Index: 991514 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0380. Min Act: -0.0002

Data Index: 94848 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0373. Min Act: -0.0002

Data Index: 845853 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0367. Min Act: -0.0002

Data Index: 94782 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1136524 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0353. Min Act: -0.0002

Data Index: 1411564 (Python Code)

Max Activating Token Index: 482

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0361. Min Act: -0.0002

Data Index: 530313 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0349. Min Act: -0.0002

Data Index: 721401 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0347. Min Act: -0.0002

Data Index: 329592 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0347. Min Act: -0.0002

Data Index: 956260 (C4 (Web Text))

Max Activating Token Index: 97