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

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

Neuron 5 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5969. Min Range: -8.5969

Max Act: 8.5969. Min Act: -0.0000

Data Index: 1200527 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.3129. Min Act: -0.0000

Data Index: 755593 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.7372. Min Act: -0.0000

Data Index: 520223 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.3653. Min Act: -0.0001

Data Index: 861923 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.2333. Min Act: -0.0000

Data Index: 134265 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.5153. Min Act: -0.0001

Data Index: 813797 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.1791. Min Act: -0.0000

Data Index: 59964 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.5011. Min Act: -0.0000

Data Index: 870874 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 8.5969. Min Range: -8.5969

Max Act: 6.9528. Min Act: -0.0000

Data Index: 509522 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.0916. Min Act: -0.0001

Data Index: 930646 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.2284. Min Act: -0.0000

Data Index: 477691 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.1723. Min Act: -0.0000

Data Index: 402572 (C4 (Web Text))

Max Activating Token Index: 678

Text #12

Max Range: 8.5969. Min Range: -8.5969

Max Act: 6.6066. Min Act: -0.0001

Data Index: 698604 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 8.5969. Min Range: -8.5969

Max Act: 6.9401. Min Act: -0.0000

Data Index: 532218 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 8.5969. Min Range: -8.5969

Max Act: 6.8924. Min Act: -0.0001

Data Index: 887931 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 8.5969. Min Range: -8.5969

Max Act: 6.5746. Min Act: -0.0000

Data Index: 1268882 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.1921. Min Act: -0.0000

Data Index: 962988 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 8.5969. Min Range: -8.5969

Max Act: 7.1413. Min Act: -0.0000

Data Index: 1307558 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 8.5969. Min Range: -8.5969

Max Act: 6.3044. Min Act: -0.0000

Data Index: 1282986 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 8.5969. Min Range: -8.5969

Max Act: 6.9907. Min Act: -0.0000

Data Index: 285195 (C4 (Web Text))

Max Activating Token Index: 395