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

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

Neuron 3329 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: 3.5395. Min Range: -3.5395

Max Act: 3.4193. Min Act: -0.0001

Data Index: 258506 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3855. Min Act: -0.0000

Data Index: 1011666 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.3129. Min Act: -0.0001

Data Index: 806137 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.5395. Min Act: -0.0001

Data Index: 582344 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.1722. Min Act: -0.0001

Data Index: 1118335 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.0393. Min Act: -0.0001

Data Index: 649346 (C4 (Web Text))

Max Activating Token Index: 723

Text #6

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.1010. Min Act: -0.0001

Data Index: 203845 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.9189. Min Act: -0.0001

Data Index: 821671 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.0546. Min Act: -0.0001

Data Index: 411812 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.0266. Min Act: -0.0001

Data Index: 703795 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 3.5395. Min Range: -3.5395

Max Act: 3.0145. Min Act: -0.0000

Data Index: 776920 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.6521. Min Act: -0.0001

Data Index: 1247651 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.9184. Min Act: -0.0000

Data Index: 638764 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.9141. Min Act: -0.0001

Data Index: 1020755 (C4 (Web Text))

Max Activating Token Index: 938

Text #14

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.6992. Min Act: -0.0001

Data Index: 1337371 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.6847. Min Act: -0.0001

Data Index: 1166463 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.6816. Min Act: -0.0001

Data Index: 899904 (C4 (Web Text))

Max Activating Token Index: 994

Text #17

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.6830. Min Act: -0.0000

Data Index: 293771 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.8074. Min Act: -0.0000

Data Index: 201262 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 3.5395. Min Range: -3.5395

Max Act: 2.7899. Min Act: -0.0001

Data Index: 1297587 (C4 (Web Text))

Max Activating Token Index: 466