Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3633 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1421. Min Range: -1.1421

Max Act: 1.1421. Min Act: -0.0001

Data Index: 359787 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9496. Min Act: -0.0001

Data Index: 452922 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8854. Min Act: -0.0001

Data Index: 1212736 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9087. Min Act: -0.0001

Data Index: 324746 (C4 (Web Text))

Max Activating Token Index: 753

Text #4

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8508. Min Act: -0.0001

Data Index: 641823 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9588. Min Act: -0.0000

Data Index: 26050 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9019. Min Act: -0.0001

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1218190 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8027. Min Act: -0.0001

Data Index: 1213533 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8482. Min Act: -0.0001

Data Index: 612961 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8154. Min Act: -0.0001

Data Index: 1431296 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8062. Min Act: -0.0001

Data Index: 872580 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.9051. Min Act: -0.0001

Data Index: 1023193 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7858. Min Act: -0.0000

Data Index: 3509 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1552994 (Python Code)

Max Activating Token Index: 512

Text #15

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7775. Min Act: -0.0001

Data Index: 81655 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7779. Min Act: -0.0001

Data Index: 215081 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1112631 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7616. Min Act: -0.0001

Data Index: 594649 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 1.1421. Min Range: -1.1421

Max Act: 0.7403. Min Act: -0.0001

Data Index: 345027 (C4 (Web Text))

Max Activating Token Index: 988