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

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

Neuron 4213 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: 0.6105. Min Range: -0.6105

Max Act: 0.5298. Min Act: 0.0000

Data Index: 696868 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1612843 (Python Code)

Max Activating Token Index: 796

Text #2

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.5344. Min Act: -0.0000

Data Index: 518678 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.5432. Min Act: -0.0000

Data Index: 782724 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.5077. Min Act: 0.0000

Data Index: 512164 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1220097 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4687. Min Act: -0.0000

Data Index: 192243 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.5302. Min Act: 0.0000

Data Index: 1040814 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4743. Min Act: 0.0000

Data Index: 1212626 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4834. Min Act: 0.0000

Data Index: 705767 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4941. Min Act: 0.0000

Data Index: 1139471 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1408540 (Python Code)

Max Activating Token Index: 1012

Text #12

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4929. Min Act: 0.0001

Data Index: 1032679 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4749. Min Act: 0.0000

Data Index: 31486 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4744. Min Act: 0.0000

Data Index: 714415 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4808. Min Act: -0.0000

Data Index: 428926 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4938. Min Act: -0.0000

Data Index: 309096 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4594. Min Act: 0.0000

Data Index: 810128 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.6105. Min Range: -0.6105

Max Act: 0.4785. Min Act: -0.0000

Data Index: 800871 (C4 (Web Text))

Max Activating Token Index: 759