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

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

Neuron 2333 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: 1.0876. Min Range: -1.0876

Max Act: 1.0876. Min Act: -0.0002

Data Index: 1115361 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8772. Min Act: -0.0001

Data Index: 739483 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8868. Min Act: -0.0002

Data Index: 539248 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.9020. Min Act: -0.0002

Data Index: 105656 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8727. Min Act: -0.0001

Data Index: 82819 (C4 (Web Text))

Max Activating Token Index: 502

Text #5

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8142. Min Act: -0.0002

Data Index: 1166180 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8356. Min Act: -0.0001

Data Index: 985898 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8862. Min Act: -0.0002

Data Index: 296687 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8175. Min Act: -0.0001

Data Index: 1292724 (C4 (Web Text))

Max Activating Token Index: 13

Text #9

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8151. Min Act: -0.0002

Data Index: 624398 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7885. Min Act: -0.0002

Data Index: 345558 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8395. Min Act: -0.0002

Data Index: 422091 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7662. Min Act: -0.0002

Data Index: 636688 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7903. Min Act: -0.0002

Data Index: 59388 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7814. Min Act: -0.0001

Data Index: 1135501 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7535. Min Act: -0.0001

Data Index: 814582 (C4 (Web Text))

Max Activating Token Index: 548

Text #16

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7980. Min Act: -0.0001

Data Index: 917474 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7730. Min Act: -0.0001

Data Index: 835202 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.7718. Min Act: -0.0002

Data Index: 285917 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 1.0876. Min Range: -1.0876

Max Act: 0.8320. Min Act: -0.0001

Data Index: 1117183 (C4 (Web Text))

Max Activating Token Index: 249