Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2182 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1081734 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0488. Min Act: 0.0001

Data Index: 530022 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0503. Min Act: -0.0001

Data Index: 452476 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0501. Min Act: -0.0000

Data Index: 196570 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0503. Min Act: -0.0001

Data Index: 525249 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0490. Min Act: -0.0000

Data Index: 318065 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0448. Min Act: -0.0000

Data Index: 77131 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0453. Min Act: -0.0001

Data Index: 314027 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0448. Min Act: 0.0000

Data Index: 898087 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0439. Min Act: -0.0001

Data Index: 1054068 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0421. Min Act: -0.0000

Data Index: 230829 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0431. Min Act: -0.0001

Data Index: 1440669 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0415. Min Act: 0.0000

Data Index: 449145 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1251242 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0403. Min Act: -0.0000

Data Index: 625641 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1647690 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0411. Min Act: -0.0001

Data Index: 373138 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0392. Min Act: 0.0000

Data Index: 640199 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0393. Min Act: -0.0000

Data Index: 230682 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.0795. Min Range: -0.0795

Max Act: 0.0420. Min Act: -0.0000

Data Index: 783953 (C4 (Web Text))

Max Activating Token Index: 200