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

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

Neuron 3816 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: 0.5134. Min Range: -0.5134

Max Act: 0.4915. Min Act: -0.0001

Data Index: 515790 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1270982 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.5134. Min Act: -0.0001

Data Index: 160546 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4811. Min Act: -0.0001

Data Index: 398693 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4625. Min Act: -0.0001

Data Index: 449650 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4331. Min Act: -0.0001

Data Index: 365035 (C4 (Web Text))

Max Activating Token Index: 747

Text #6

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4682. Min Act: -0.0001

Data Index: 321551 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4591. Min Act: -0.0001

Data Index: 1328902 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4435. Min Act: -0.0001

Data Index: 1039526 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4353. Min Act: -0.0001

Data Index: 1315095 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4203. Min Act: -0.0001

Data Index: 1346228 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4535. Min Act: -0.0001

Data Index: 1405530 (Python Code)

Max Activating Token Index: 943

Text #12

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4213. Min Act: -0.0001

Data Index: 350910 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4271. Min Act: -0.0001

Data Index: 648540 (C4 (Web Text))

Max Activating Token Index: 526

Text #14

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4469. Min Act: -0.0001

Data Index: 802169 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4508. Min Act: -0.0001

Data Index: 1125791 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4141. Min Act: -0.0001

Data Index: 958679 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4311. Min Act: -0.0001

Data Index: 1145847 (C4 (Web Text))

Max Activating Token Index: 353

Text #18

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4104. Min Act: -0.0001

Data Index: 125700 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.5134. Min Range: -0.5134

Max Act: 0.4304. Min Act: -0.0001

Data Index: 418726 (C4 (Web Text))

Max Activating Token Index: 624