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

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

Neuron 2923 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: 3.0959. Min Range: -3.0959

Max Act: 3.0959. Min Act: -0.0002

Data Index: 604868 (C4 (Web Text))

Max Activating Token Index: 727

Text #1

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.9729. Min Act: -0.0003

Data Index: 1109303 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.8874. Min Act: -0.0002

Data Index: 440734 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.7959. Min Act: -0.0002

Data Index: 1003439 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.7980. Min Act: -0.0002

Data Index: 593556 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.7328. Min Act: -0.0002

Data Index: 1320078 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.6707. Min Act: -0.0002

Data Index: 1003330 (C4 (Web Text))

Max Activating Token Index: 805

Text #7

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.6428. Min Act: -0.0002

Data Index: 1232880 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.6998. Min Act: -0.0002

Data Index: 187449 (C4 (Web Text))

Max Activating Token Index: 898

Text #9

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.6913. Min Act: -0.0002

Data Index: 1265618 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.5679. Min Act: -0.0002

Data Index: 763967 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.5809. Min Act: -0.0002

Data Index: 547335 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.5784. Min Act: -0.0002

Data Index: 1089425 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.5511. Min Act: -0.0002

Data Index: 536067 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.6023. Min Act: -0.0002

Data Index: 913033 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.5685. Min Act: -0.0002

Data Index: 540095 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.5575. Min Act: -0.0002

Data Index: 490369 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.6034. Min Act: -0.0002

Data Index: 324209 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.6387. Min Act: -0.0002

Data Index: 245860 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 3.0959. Min Range: -3.0959

Max Act: 2.4896. Min Act: -0.0002

Data Index: 236689 (C4 (Web Text))

Max Activating Token Index: 773