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

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

Neuron 5505 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: 0.4262. Min Range: -0.4262

Max Act: 0.4262. Min Act: -0.0001

Data Index: 333044 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3371. Min Act: -0.0001

Data Index: 10777 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3412. Min Act: -0.0001

Data Index: 470713 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2868. Min Act: -0.0001

Data Index: 655805 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.3149. Min Act: -0.0001

Data Index: 1205798 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2640. Min Act: -0.0001

Data Index: 1252869 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2753. Min Act: -0.0001

Data Index: 674583 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2887. Min Act: -0.0001

Data Index: 213460 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2671. Min Act: -0.0001

Data Index: 1126342 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2563. Min Act: -0.0001

Data Index: 53756 (C4 (Web Text))

Max Activating Token Index: 1000

Text #10

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2420. Min Act: -0.0001

Data Index: 1020388 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1179123 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2858. Min Act: -0.0001

Data Index: 1423144 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2595. Min Act: -0.0001

Data Index: 1255080 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2365. Min Act: -0.0001

Data Index: 1087393 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2028. Min Act: -0.0001

Data Index: 1214958 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2330. Min Act: -0.0001

Data Index: 169698 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2304. Min Act: -0.0001

Data Index: 1111109 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2296. Min Act: -0.0001

Data Index: 75518 (C4 (Web Text))

Max Activating Token Index: 313

Text #19

Max Range: 0.4262. Min Range: -0.4262

Max Act: 0.2363. Min Act: -0.0001

Data Index: 118481 (C4 (Web Text))

Max Activating Token Index: 8