Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 472 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0808. Min Act: -0.0002

Data Index: 689022 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0002

Data Index: 500566 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0795. Min Act: -0.0001

Data Index: 383810 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1055036 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0780. Min Act: -0.0001

Data Index: 927420 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0814. Min Act: -0.0002

Data Index: 250114 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0733. Min Act: -0.0002

Data Index: 938967 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0725. Min Act: -0.0001

Data Index: 932301 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1258644 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0758. Min Act: -0.0001

Data Index: 466120 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0762. Min Act: -0.0001

Data Index: 1244466 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1023228 (C4 (Web Text))

Max Activating Token Index: 674

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1118597 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0707. Min Act: -0.0001

Data Index: 968496 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0726. Min Act: -0.0002

Data Index: 733665 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0741. Min Act: -0.0001

Data Index: 772649 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0741. Min Act: -0.0002

Data Index: 61230 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0700. Min Act: -0.0001

Data Index: 782370 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1187363 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1253926 (C4 (Web Text))

Max Activating Token Index: 599