Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1945 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0005

Data Index: 838785 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0949. Min Act: -0.0005

Data Index: 1087184 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0912. Min Act: -0.0005

Data Index: 797837 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0838. Min Act: -0.0005

Data Index: 813015 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0808. Min Act: -0.0005

Data Index: 539180 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0806. Min Act: -0.0005

Data Index: 992574 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0839. Min Act: -0.0006

Data Index: 889474 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0788. Min Act: -0.0006

Data Index: 503821 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0788. Min Act: -0.0005

Data Index: 15553 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0762. Min Act: -0.0005

Data Index: 348306 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0728. Min Act: -0.0005

Data Index: 582295 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0756. Min Act: -0.0005

Data Index: 4197 (C4 (Web Text))

Max Activating Token Index: 595

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0742. Min Act: -0.0005

Data Index: 1192020 (C4 (Web Text))

Max Activating Token Index: 974

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0703. Min Act: -0.0005

Data Index: 444581 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0763. Min Act: -0.0005

Data Index: 1128802 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0728. Min Act: -0.0006

Data Index: 1312370 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0722. Min Act: -0.0006

Data Index: 1202524 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0689. Min Act: -0.0005

Data Index: 94930 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0711. Min Act: -0.0005

Data Index: 284127 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0679. Min Act: -0.0006

Data Index: 1313036 (C4 (Web Text))

Max Activating Token Index: 587