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

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

Neuron 2008 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: 1.8721. Min Range: -1.8721

Max Act: 1.5527. Min Act: -0.0001

Data Index: 102379 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4495. Min Act: -0.0001

Data Index: 635928 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.5353. Min Act: -0.0001

Data Index: 958330 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.8721. Min Act: -0.0001

Data Index: 1295514 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4445. Min Act: -0.0001

Data Index: 812808 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.4207. Min Act: -0.0001

Data Index: 71803 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.7240. Min Act: -0.0001

Data Index: 547264 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3168. Min Act: -0.0001

Data Index: 1277971 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2980. Min Act: -0.0001

Data Index: 12465 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2357. Min Act: -0.0001

Data Index: 1337732 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2658. Min Act: -0.0001

Data Index: 263726 (C4 (Web Text))

Max Activating Token Index: 593

Text #11

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3468. Min Act: -0.0001

Data Index: 49817 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2621. Min Act: -0.0001

Data Index: 313479 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.3364. Min Act: -0.0001

Data Index: 699082 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.1634. Min Act: -0.0001

Data Index: 613848 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2360. Min Act: -0.0001

Data Index: 1345154 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2280. Min Act: -0.0001

Data Index: 1333217 (C4 (Web Text))

Max Activating Token Index: 993

Text #17

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.1899. Min Act: -0.0001

Data Index: 289870 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.1147. Min Act: -0.0001

Data Index: 34962 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 1.8721. Min Range: -1.8721

Max Act: 1.2155. Min Act: -0.0001

Data Index: 1265745 (C4 (Web Text))

Max Activating Token Index: 261