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

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

Neuron 5110 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0522. Min Range: -1.0522

Max Act: 1.0522. Min Act: -0.0001

Data Index: 140329 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9918. Min Act: -0.0001

Data Index: 1038405 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9186. Min Act: -0.0001

Data Index: 1262701 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9512. Min Act: -0.0001

Data Index: 296961 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8623. Min Act: -0.0001

Data Index: 479579 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8690. Min Act: -0.0001

Data Index: 1321252 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8590. Min Act: -0.0001

Data Index: 55030 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8393. Min Act: -0.0001

Data Index: 978123 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.7959. Min Act: -0.0001

Data Index: 72159 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.9033. Min Act: -0.0001

Data Index: 842066 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8645. Min Act: -0.0001

Data Index: 474010 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.7614. Min Act: -0.0001

Data Index: 1306090 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8807. Min Act: -0.0001

Data Index: 54440 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8952. Min Act: -0.0001

Data Index: 47746 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8167. Min Act: -0.0001

Data Index: 406004 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8453. Min Act: -0.0001

Data Index: 70047 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8378. Min Act: -0.0001

Data Index: 54581 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.7778. Min Act: -0.0001

Data Index: 1242354 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8708. Min Act: -0.0001

Data Index: 199410 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 1.0522. Min Range: -1.0522

Max Act: 0.8028. Min Act: -0.0001

Data Index: 196499 (C4 (Web Text))

Max Activating Token Index: 504