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

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

Neuron 210 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: 4.5715. Min Range: -4.5715

Max Act: 4.4476. Min Act: -0.0000

Data Index: 242206 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 4.5715. Min Range: -4.5715

Max Act: 4.5715. Min Act: -0.0000

Data Index: 429013 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 4.5715. Min Range: -4.5715

Max Act: 4.5394. Min Act: -0.0000

Data Index: 1033073 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 4.5715. Min Range: -4.5715

Max Act: 4.1469. Min Act: -0.0000

Data Index: 1309368 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 4.5715. Min Range: -4.5715

Max Act: 4.0318. Min Act: -0.0000

Data Index: 178444 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.9629. Min Act: -0.0000

Data Index: 688340 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.6253. Min Act: -0.0000

Data Index: 233621 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.6883. Min Act: -0.0000

Data Index: 595436 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.4776. Min Act: -0.0000

Data Index: 104815 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.7789. Min Act: -0.0000

Data Index: 901568 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.3574. Min Act: -0.0000

Data Index: 491559 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.4785. Min Act: -0.0000

Data Index: 1064174 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.3166. Min Act: -0.0000

Data Index: 1310549 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.4784. Min Act: -0.0000

Data Index: 221360 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.5514. Min Act: -0.0000

Data Index: 785033 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.5535. Min Act: -0.0000

Data Index: 38333 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.3774. Min Act: -0.0000

Data Index: 93636 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.1320. Min Act: -0.0000

Data Index: 572904 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.1380. Min Act: -0.0000

Data Index: 466865 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 4.5715. Min Range: -4.5715

Max Act: 3.2498. Min Act: -0.0000

Data Index: 75857 (C4 (Web Text))

Max Activating Token Index: 365