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

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

Neuron 4365 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: 1.3617. Min Range: -1.3617

Max Act: 1.3617. Min Act: -0.0002

Data Index: 703285 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.3580. Min Act: -0.0002

Data Index: 985595 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.3230. Min Act: -0.0002

Data Index: 1078670 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.3335. Min Act: -0.0002

Data Index: 1147181 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2949. Min Act: -0.0002

Data Index: 551270 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.3200. Min Act: -0.0002

Data Index: 1285587 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.3014. Min Act: -0.0002

Data Index: 61821 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2953. Min Act: -0.0002

Data Index: 779108 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2821. Min Act: -0.0002

Data Index: 1136417 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2635. Min Act: -0.0002

Data Index: 1090796 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2791. Min Act: -0.0002

Data Index: 943808 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2837. Min Act: -0.0002

Data Index: 1036683 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2695. Min Act: -0.0002

Data Index: 339941 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2877. Min Act: -0.0002

Data Index: 1325622 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2800. Min Act: -0.0002

Data Index: 760729 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2587. Min Act: -0.0002

Data Index: 407260 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2219. Min Act: -0.0002

Data Index: 834434 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2499. Min Act: -0.0002

Data Index: 235393 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2667. Min Act: -0.0002

Data Index: 924294 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 1.3617. Min Range: -1.3617

Max Act: 1.2821. Min Act: -0.0002

Data Index: 684485 (C4 (Web Text))

Max Activating Token Index: 4