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

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

Neuron 2511 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1615. Min Act: -0.0003

Data Index: 677841 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1326353 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1078. Min Act: -0.0003

Data Index: 906776 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1065. Min Act: -0.0003

Data Index: 278599 (C4 (Web Text))

Max Activating Token Index: 556

Text #4

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0932. Min Act: -0.0003

Data Index: 890201 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0968. Min Act: -0.0003

Data Index: 316761 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0927. Min Act: -0.0003

Data Index: 241092 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0885. Min Act: -0.0002

Data Index: 117989 (C4 (Web Text))

Max Activating Token Index: 490

Text #8

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0940. Min Act: -0.0003

Data Index: 314435 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0846. Min Act: -0.0002

Data Index: 666589 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0883. Min Act: -0.0003

Data Index: 1106116 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0814. Min Act: -0.0003

Data Index: 847769 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0751. Min Act: -0.0002

Data Index: 409479 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0776. Min Act: -0.0003

Data Index: 651859 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0975. Min Act: -0.0003

Data Index: 494540 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0747. Min Act: -0.0003

Data Index: 218609 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1177637 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0860. Min Act: -0.0002

Data Index: 494687 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0732. Min Act: -0.0003

Data Index: 780971 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.0784. Min Act: -0.0003

Data Index: 931604 (C4 (Web Text))

Max Activating Token Index: 735