Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4357 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3498. Min Range: -2.3498

Max Act: 2.3498. Min Act: -0.0000

Data Index: 27339 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.7445. Min Act: -0.0000

Data Index: 224160 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.5362. Min Act: -0.0000

Data Index: 911035 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1229848 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.5139. Min Act: -0.0000

Data Index: 422903 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.2508. Min Act: -0.0000

Data Index: 463130 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.1768. Min Act: -0.0000

Data Index: 39268 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.1872. Min Act: -0.0000

Data Index: 84873 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.1410. Min Act: -0.0000

Data Index: 978571 (C4 (Web Text))

Max Activating Token Index: 37

Text #9

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.2253. Min Act: -0.0000

Data Index: 15701 (C4 (Web Text))

Max Activating Token Index: 495

Text #10

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.1372. Min Act: -0.0000

Data Index: 1102596 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.0997. Min Act: -0.0000

Data Index: 418975 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1210755 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.1285. Min Act: -0.0000

Data Index: 833670 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.0557. Min Act: -0.0000

Data Index: 512123 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.1096. Min Act: -0.0000

Data Index: 522232 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.0673. Min Act: -0.0000

Data Index: 164094 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.0719. Min Act: -0.0000

Data Index: 1069949 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1267822 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 2.3498. Min Range: -2.3498

Max Act: 1.0168. Min Act: -0.0000

Data Index: 734742 (C4 (Web Text))

Max Activating Token Index: 53