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

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

Neuron 5522 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: 0.0991. Min Range: -0.0991

Max Act: 0.0991. Min Act: -0.0002

Data Index: 377363 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0933. Min Act: -0.0002

Data Index: 399163 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0926. Min Act: -0.0002

Data Index: 372743 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0948. Min Act: -0.0002

Data Index: 840790 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0940. Min Act: -0.0003

Data Index: 616320 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0820. Min Act: -0.0002

Data Index: 299944 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0833. Min Act: -0.0002

Data Index: 439489 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0822. Min Act: -0.0003

Data Index: 455563 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1217444 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0815. Min Act: -0.0002

Data Index: 850570 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0790. Min Act: -0.0002

Data Index: 585585 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0780. Min Act: -0.0002

Data Index: 196997 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1019810 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0777. Min Act: -0.0002

Data Index: 81391 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0789. Min Act: -0.0002

Data Index: 742555 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0771. Min Act: -0.0002

Data Index: 836263 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0762. Min Act: -0.0003

Data Index: 4097 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0752. Min Act: -0.0002

Data Index: 83704 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0744. Min Act: -0.0002

Data Index: 502389 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0739. Min Act: -0.0002

Data Index: 251455 (C4 (Web Text))

Max Activating Token Index: 921