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

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

Neuron 5697 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: 3.9510. Min Range: -3.9510

Max Act: 3.9510. Min Act: -0.0001

Data Index: 1113178 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.6645. Min Act: -0.0001

Data Index: 1358638 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.7459. Min Act: -0.0001

Data Index: 712849 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.5914. Min Act: -0.0001

Data Index: 263908 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.5424. Min Act: -0.0001

Data Index: 643016 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.6692. Min Act: -0.0001

Data Index: 851191 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.7578. Min Act: -0.0001

Data Index: 275669 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.6591. Min Act: -0.0001

Data Index: 158158 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.5520. Min Act: -0.0001

Data Index: 250749 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.3751. Min Act: -0.0001

Data Index: 132880 (C4 (Web Text))

Max Activating Token Index: 106

Text #10

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.5513. Min Act: -0.0001

Data Index: 248238 (C4 (Web Text))

Max Activating Token Index: 504

Text #11

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.6177. Min Act: -0.0001

Data Index: 771451 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.3148. Min Act: -0.0001

Data Index: 646782 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.6128. Min Act: -0.0001

Data Index: 565562 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.4996. Min Act: -0.0001

Data Index: 513785 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.3935. Min Act: -0.0001

Data Index: 782946 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.2709. Min Act: -0.0001

Data Index: 488250 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.1864. Min Act: -0.0001

Data Index: 932493 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.2624. Min Act: -0.0001

Data Index: 149612 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 3.9510. Min Range: -3.9510

Max Act: 3.3267. Min Act: -0.0001

Data Index: 886661 (C4 (Web Text))

Max Activating Token Index: 538