Model: SoLU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 516 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0949. Min Act: -0.0003

Data Index: 91088 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0002

Data Index: 131528 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0890. Min Act: -0.0002

Data Index: 825549 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0900. Min Act: -0.0002

Data Index: 994721 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0896. Min Act: -0.0002

Data Index: 53970 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0868. Min Act: -0.0002

Data Index: 887799 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1075728 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0851. Min Act: -0.0001

Data Index: 917606 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1303669 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0803. Min Act: -0.0003

Data Index: 526629 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1141540 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0785. Min Act: -0.0002

Data Index: 626701 (C4 (Web Text))

Max Activating Token Index: 906

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0794. Min Act: -0.0002

Data Index: 179785 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0800. Min Act: -0.0002

Data Index: 761963 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0790. Min Act: -0.0002

Data Index: 362187 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0777. Min Act: -0.0002

Data Index: 652818 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0765. Min Act: -0.0002

Data Index: 473961 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0778. Min Act: -0.0002

Data Index: 838312 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0774. Min Act: -0.0002

Data Index: 705793 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0792. Min Act: -0.0002

Data Index: 796637 (C4 (Web Text))

Max Activating Token Index: 426