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

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

Neuron 2621 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: 0.4768. Min Range: -0.4768

Max Act: 0.4768. Min Act: -0.0000

Data Index: 1201364 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4420. Min Act: -0.0000

Data Index: 1119064 (C4 (Web Text))

Max Activating Token Index: 615

Text #2

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.4126. Min Act: -0.0000

Data Index: 694747 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3928. Min Act: -0.0000

Data Index: 603391 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3520. Min Act: -0.0000

Data Index: 693917 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3519. Min Act: -0.0000

Data Index: 1190315 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3625. Min Act: -0.0000

Data Index: 711989 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3233. Min Act: -0.0000

Data Index: 231636 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1193177 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3295. Min Act: -0.0000

Data Index: 751671 (C4 (Web Text))

Max Activating Token Index: 428

Text #10

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1224752 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3528. Min Act: -0.0000

Data Index: 770291 (C4 (Web Text))

Max Activating Token Index: 981

Text #12

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1141429 (C4 (Web Text))

Max Activating Token Index: 20

Text #13

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3354. Min Act: -0.0000

Data Index: 554478 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3128. Min Act: -0.0000

Data Index: 317782 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3186. Min Act: 0.0000

Data Index: 129587 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.3523. Min Act: -0.0000

Data Index: 278642 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2960. Min Act: -0.0000

Data Index: 944367 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2960. Min Act: -0.0000

Data Index: 154467 (C4 (Web Text))

Max Activating Token Index: 641

Text #19

Max Range: 0.4768. Min Range: -0.4768

Max Act: 0.2592. Min Act: -0.0000

Data Index: 502478 (C4 (Web Text))

Max Activating Token Index: 865