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

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

Neuron 1400 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.5157. Min Act: -0.0001

Data Index: 603188 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1198268 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1154869 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4209. Min Act: -0.0000

Data Index: 526722 (C4 (Web Text))

Max Activating Token Index: 679

Text #4

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4428. Min Act: -0.0000

Data Index: 838867 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4245. Min Act: -0.0000

Data Index: 848569 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1025469 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1059405 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4133. Min Act: -0.0000

Data Index: 122749 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3936. Min Act: -0.0000

Data Index: 477565 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3960. Min Act: -0.0001

Data Index: 394631 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1286756 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3861. Min Act: -0.0001

Data Index: 259088 (C4 (Web Text))

Max Activating Token Index: 574

Text #13

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3768. Min Act: -0.0001

Data Index: 302046 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.4256. Min Act: -0.0000

Data Index: 1261344 (C4 (Web Text))

Max Activating Token Index: 848

Text #15

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3719. Min Act: -0.0000

Data Index: 675372 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1029825 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3476. Min Act: -0.0000

Data Index: 454755 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3557. Min Act: -0.0000

Data Index: 699416 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.5157. Min Range: -0.5157

Max Act: 0.3542. Min Act: -0.0001

Data Index: 1148095 (C4 (Web Text))

Max Activating Token Index: 205