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

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

Neuron 20 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: 1.3102. Min Range: -1.3102

Max Act: 1.2906. Min Act: -0.0000

Data Index: 987447 (C4 (Web Text))

Max Activating Token Index: 562

Text #1

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.3004. Min Act: -0.0000

Data Index: 167289 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.0386. Min Act: -0.0000

Data Index: 299130 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.0653. Min Act: -0.0000

Data Index: 180600 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9908. Min Act: -0.0000

Data Index: 79937 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.0926. Min Act: -0.0001

Data Index: 790344 (C4 (Web Text))

Max Activating Token Index: 533

Text #6

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.3102. Min Act: -0.0000

Data Index: 1257652 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.0517. Min Act: -0.0000

Data Index: 921265 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1159045 (C4 (Web Text))

Max Activating Token Index: 467

Text #9

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.0119. Min Act: -0.0000

Data Index: 138932 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1178336 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9263. Min Act: -0.0000

Data Index: 754100 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9723. Min Act: -0.0000

Data Index: 964274 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9972. Min Act: -0.0000

Data Index: 1055777 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9199. Min Act: -0.0000

Data Index: 1327957 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1259221 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1193360 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1292172 (C4 (Web Text))

Max Activating Token Index: 268

Text #18

Max Range: 1.3102. Min Range: -1.3102

Max Act: 1.0105. Min Act: -0.0001

Data Index: 349669 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 1.3102. Min Range: -1.3102

Max Act: 0.9157. Min Act: -0.0000

Data Index: 421401 (C4 (Web Text))

Max Activating Token Index: 525