Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3056 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4590. Min Act: -0.0000

Data Index: 1640244 (Python Code)

Max Activating Token Index: 527

Text #1

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.4150. Min Act: -0.0000

Data Index: 1581070 (Python Code)

Max Activating Token Index: 488

Text #2

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3953. Min Act: -0.0000

Data Index: 601507 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1635814 (Python Code)

Max Activating Token Index: 672

Text #4

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3566. Min Act: -0.0000

Data Index: 839936 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3583. Min Act: -0.0000

Data Index: 567247 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1404617 (Python Code)

Max Activating Token Index: 66

Text #7

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3034. Min Act: -0.0000

Data Index: 1354254 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3190. Min Act: -0.0000

Data Index: 193574 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3149. Min Act: -0.0000

Data Index: 681739 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.3006. Min Act: -0.0000

Data Index: 666790 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2876. Min Act: -0.0000

Data Index: 688828 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2966. Min Act: -0.0000

Data Index: 922787 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1169591 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2788. Min Act: -0.0000

Data Index: 1086284 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2664. Min Act: -0.0000

Data Index: 708610 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2561. Min Act: -0.0000

Data Index: 752235 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2823. Min Act: -0.0000

Data Index: 46390 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2834. Min Act: -0.0000

Data Index: 812218 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.4590. Min Range: -0.4590

Max Act: 0.2770. Min Act: -0.0000

Data Index: 968648 (C4 (Web Text))

Max Activating Token Index: 598