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

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

Neuron 5845 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: 0.0948. Min Range: -0.0948

Max Act: 0.0945. Min Act: -0.0002

Data Index: 1330276 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0002

Data Index: 822580 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0915. Min Act: -0.0002

Data Index: 233479 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0920. Min Act: -0.0002

Data Index: 359271 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0925. Min Act: -0.0002

Data Index: 354912 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1150758 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0883. Min Act: -0.0002

Data Index: 658163 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1359469 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0893. Min Act: -0.0002

Data Index: 586178 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0891. Min Act: -0.0002

Data Index: 478682 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0892. Min Act: -0.0002

Data Index: 1066815 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0846. Min Act: -0.0002

Data Index: 114524 (C4 (Web Text))

Max Activating Token Index: 955

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0855. Min Act: -0.0002

Data Index: 763190 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0854. Min Act: -0.0002

Data Index: 214032 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0836. Min Act: -0.0002

Data Index: 998685 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0850. Min Act: -0.0002

Data Index: 199999 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1181457 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0845. Min Act: -0.0002

Data Index: 543335 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0837. Min Act: -0.0002

Data Index: 674949 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1090916 (C4 (Web Text))

Max Activating Token Index: 641