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

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

Neuron 4606 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3706. Min Range: -3.3706

Max Act: 3.3706. Min Act: -0.0000

Data Index: 1013767 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.9157. Min Act: -0.0000

Data Index: 1158181 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.7008. Min Act: -0.0000

Data Index: 712915 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.9029. Min Act: -0.0000

Data Index: 1251943 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.7400. Min Act: -0.0000

Data Index: 274380 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.6256. Min Act: -0.0000

Data Index: 652169 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.7089. Min Act: -0.0000

Data Index: 468850 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.8192. Min Act: -0.0000

Data Index: 489402 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.6848. Min Act: -0.0000

Data Index: 257943 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.6863. Min Act: -0.0000

Data Index: 846953 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.7995. Min Act: -0.0000

Data Index: 655719 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.6459. Min Act: -0.0000

Data Index: 905731 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.6579. Min Act: -0.0000

Data Index: 1239622 (C4 (Web Text))

Max Activating Token Index: 422

Text #13

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.7075. Min Act: -0.0000

Data Index: 868289 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.5178. Min Act: -0.0000

Data Index: 1358563 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.3646. Min Act: -0.0000

Data Index: 1650591 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.4839. Min Act: -0.0000

Data Index: 495816 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.3569. Min Act: -0.0000

Data Index: 1364199 (Python Code)

Max Activating Token Index: 856

Text #18

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.4529. Min Act: -0.0000

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 3.3706. Min Range: -3.3706

Max Act: 2.3730. Min Act: -0.0000

Data Index: 243880 (C4 (Web Text))

Max Activating Token Index: 13