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

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

Neuron 3043 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0935. Min Act: -0.0002

Data Index: 1256315 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0789. Min Act: -0.0002

Data Index: 584008 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0754. Min Act: -0.0002

Data Index: 310080 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0754. Min Act: -0.0002

Data Index: 198885 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0762. Min Act: -0.0002

Data Index: 719857 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1047405 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0732. Min Act: -0.0001

Data Index: 526100 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0692. Min Act: -0.0001

Data Index: 745916 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0697. Min Act: -0.0002

Data Index: 904427 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0716. Min Act: -0.0002

Data Index: 699341 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0578. Min Act: -0.0001

Data Index: 255684 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0623. Min Act: -0.0002

Data Index: 475822 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0682. Min Act: -0.0002

Data Index: 984261 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0622. Min Act: -0.0001

Data Index: 183260 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0641. Min Act: -0.0002

Data Index: 76958 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0615. Min Act: -0.0002

Data Index: 159195 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0658. Min Act: -0.0001

Data Index: 509088 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0612. Min Act: -0.0001

Data Index: 268210 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0595. Min Act: -0.0002

Data Index: 971794 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.0935. Min Range: -0.0935

Max Act: 0.0588. Min Act: -0.0002

Data Index: 32509 (C4 (Web Text))

Max Activating Token Index: 276