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

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

Neuron 5578 in Layer 0

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: 0.8064. Min Range: -0.8064

Max Act: 0.8064. Min Act: -0.0001

Data Index: 75839 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.8051. Min Act: -0.0001

Data Index: 28447 (C4 (Web Text))

Max Activating Token Index: 889

Text #2

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7728. Min Act: -0.0001

Data Index: 72760 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7763. Min Act: -0.0001

Data Index: 890570 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7830. Min Act: -0.0001

Data Index: 854121 (C4 (Web Text))

Max Activating Token Index: 473

Text #5

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7796. Min Act: -0.0001

Data Index: 1234403 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7679. Min Act: -0.0001

Data Index: 406345 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7741. Min Act: -0.0001

Data Index: 686881 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7751. Min Act: -0.0001

Data Index: 462146 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7784. Min Act: -0.0001

Data Index: 693320 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7692. Min Act: -0.0001

Data Index: 318240 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7534. Min Act: -0.0001

Data Index: 434938 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7622. Min Act: -0.0001

Data Index: 108308 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7657. Min Act: -0.0001

Data Index: 797410 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7711. Min Act: -0.0001

Data Index: 296375 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7483. Min Act: -0.0001

Data Index: 1030657 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7549. Min Act: -0.0001

Data Index: 1039078 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7466. Min Act: -0.0001

Data Index: 373638 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7606. Min Act: -0.0001

Data Index: 681031 (C4 (Web Text))

Max Activating Token Index: 617

Text #19

Max Range: 0.8064. Min Range: -0.8064

Max Act: 0.7638. Min Act: -0.0001

Data Index: 81429 (C4 (Web Text))

Max Activating Token Index: 983