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

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

Neuron 4897 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9445. Min Act: -0.0000

Data Index: 354800 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0000

Data Index: 762406 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9011. Min Act: -0.0000

Data Index: 725919 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7862. Min Act: -0.0000

Data Index: 494400 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8295. Min Act: -0.0000

Data Index: 1045177 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7587. Min Act: -0.0000

Data Index: 118818 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8340. Min Act: -0.0000

Data Index: 693373 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7847. Min Act: -0.0000

Data Index: 584132 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7313. Min Act: -0.0000

Data Index: 1256649 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7298. Min Act: -0.0000

Data Index: 323455 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7294. Min Act: -0.0000

Data Index: 809021 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7647. Min Act: -0.0000

Data Index: 231344 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7725. Min Act: 0.0000

Data Index: 318983 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7575. Min Act: -0.0000

Data Index: 923361 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7594. Min Act: -0.0000

Data Index: 670139 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7137. Min Act: -0.0000

Data Index: 950333 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7938. Min Act: -0.0000

Data Index: 548813 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7539. Min Act: -0.0000

Data Index: 789876 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7485. Min Act: -0.0000

Data Index: 803952 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7432. Min Act: -0.0000

Data Index: 217550 (C4 (Web Text))

Max Activating Token Index: 647