Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2427 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4127. Min Act: -0.0000

Data Index: 1256442 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1329323 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1545471 (Python Code)

Max Activating Token Index: 335

Text #3

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1389546 (Python Code)

Max Activating Token Index: 764

Text #4

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.4165. Min Act: -0.0000

Data Index: 1090546 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3894. Min Act: -0.0000

Data Index: 1376913 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1579175 (Python Code)

Max Activating Token Index: 742

Text #7

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3836. Min Act: -0.0000

Data Index: 626912 (C4 (Web Text))

Max Activating Token Index: 66

Text #8

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3565. Min Act: -0.0000

Data Index: 784102 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1621327 (Python Code)

Max Activating Token Index: 717

Text #10

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3651. Min Act: -0.0000

Data Index: 68229 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3828. Min Act: -0.0000

Data Index: 1564219 (Python Code)

Max Activating Token Index: 622

Text #12

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3303. Min Act: -0.0000

Data Index: 192391 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1585254 (Python Code)

Max Activating Token Index: 473

Text #14

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3660. Min Act: -0.0000

Data Index: 1458022 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3770. Min Act: -0.0000

Data Index: 33218 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3716. Min Act: -0.0000

Data Index: 1433739 (Python Code)

Max Activating Token Index: 771

Text #17

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1347963 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3287. Min Act: -0.0000

Data Index: 566083 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.4165. Min Range: -0.4165

Max Act: 0.3381. Min Act: -0.0000

Data Index: 1303802 (C4 (Web Text))

Max Activating Token Index: 507