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

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

Neuron 3528 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.8106. Min Act: -0.0000

Data Index: 663998 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7393. Min Act: -0.0000

Data Index: 321572 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6787. Min Act: -0.0000

Data Index: 121733 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6068. Min Act: -0.0000

Data Index: 493279 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6211. Min Act: -0.0000

Data Index: 818889 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.6154. Min Act: -0.0000

Data Index: 909262 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5492. Min Act: -0.0000

Data Index: 845821 (C4 (Web Text))

Max Activating Token Index: 708

Text #7

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5172. Min Act: -0.0000

Data Index: 58533 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5483. Min Act: -0.0000

Data Index: 1085220 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5066. Min Act: -0.0000

Data Index: 45210 (C4 (Web Text))

Max Activating Token Index: 821

Text #10

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4460. Min Act: -0.0000

Data Index: 45691 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4353. Min Act: -0.0000

Data Index: 200973 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4782. Min Act: -0.0000

Data Index: 12980 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4248. Min Act: -0.0000

Data Index: 448143 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4253. Min Act: -0.0000

Data Index: 376147 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.3961. Min Act: -0.0000

Data Index: 377281 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4038. Min Act: -0.0000

Data Index: 442616 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4134. Min Act: -0.0000

Data Index: 285926 (C4 (Web Text))

Max Activating Token Index: 966

Text #18

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4314. Min Act: -0.0000

Data Index: 393334 (C4 (Web Text))

Max Activating Token Index: 408

Text #19

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4331. Min Act: -0.0000

Data Index: 208939 (C4 (Web Text))

Max Activating Token Index: 921