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

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

Neuron 3005 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.5859. Min Act: -0.0001

Data Index: 891091 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.4153. Min Act: -0.0001

Data Index: 706183 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.3294. Min Act: -0.0001

Data Index: 1234233 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.1249. Min Act: -0.0001

Data Index: 823401 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.9235. Min Act: -0.0001

Data Index: 403939 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.9289. Min Act: -0.0001

Data Index: 375104 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.9148. Min Act: -0.0001

Data Index: 92055 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.0138. Min Act: -0.0001

Data Index: 570048 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.1137. Min Act: -0.0001

Data Index: 582867 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.9572. Min Act: -0.0001

Data Index: 1065606 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.1276. Min Act: -0.0001

Data Index: 185041 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.0979. Min Act: -0.0001

Data Index: 1213494 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.7874. Min Act: -0.0001

Data Index: 1260678 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 3.5859. Min Range: -3.5859

Max Act: 3.1530. Min Act: -0.0001

Data Index: 591634 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.6333. Min Act: -0.0001

Data Index: 249595 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.5942. Min Act: -0.0001

Data Index: 445326 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.8538. Min Act: -0.0001

Data Index: 452997 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.5767. Min Act: -0.0001

Data Index: 96627 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.6928. Min Act: -0.0001

Data Index: 28567 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 3.5859. Min Range: -3.5859

Max Act: 2.5418. Min Act: -0.0001

Data Index: 1359665 (C4 (Web Text))

Max Activating Token Index: 812