Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2400 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0813. Min Act: -0.0002

Data Index: 192984 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0803. Min Act: -0.0002

Data Index: 567053 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0784. Min Act: -0.0002

Data Index: 677957 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1195911 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0782. Min Act: -0.0002

Data Index: 430658 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0778. Min Act: -0.0002

Data Index: 612160 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0743. Min Act: -0.0002

Data Index: 462138 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1118896 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1067022 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0739. Min Act: -0.0002

Data Index: 1324872 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1148754 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0751. Min Act: -0.0002

Data Index: 791424 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0749. Min Act: -0.0002

Data Index: 367639 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0746. Min Act: -0.0002

Data Index: 340592 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0740. Min Act: -0.0002

Data Index: 848384 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0749. Min Act: -0.0002

Data Index: 635540 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0737. Min Act: -0.0002

Data Index: 659776 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1238109 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1056744 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.0813. Min Range: -0.0813

Max Act: 0.0719. Min Act: -0.0002

Data Index: 443936 (C4 (Web Text))

Max Activating Token Index: 198