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

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

Neuron 2817 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: 0.6712. Min Range: -0.6712

Max Act: 0.6189. Min Act: -0.0000

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.6712. Min Act: -0.0000

Data Index: 238655 (C4 (Web Text))

Max Activating Token Index: 836

Text #2

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5845. Min Act: -0.0000

Data Index: 771055 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5090. Min Act: -0.0000

Data Index: 1090513 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5229. Min Act: -0.0000

Data Index: 904900 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1108998 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5081. Min Act: -0.0000

Data Index: 1145744 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4852. Min Act: -0.0000

Data Index: 50551 (C4 (Web Text))

Max Activating Token Index: 857

Text #8

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4796. Min Act: -0.0000

Data Index: 691101 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1155789 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5209. Min Act: -0.0000

Data Index: 145466 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.5179. Min Act: -0.0000

Data Index: 452532 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1080090 (C4 (Web Text))

Max Activating Token Index: 427

Text #13

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4682. Min Act: -0.0000

Data Index: 753708 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4675. Min Act: -0.0000

Data Index: 868273 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4039. Min Act: -0.0000

Data Index: 125343 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4842. Min Act: -0.0000

Data Index: 248849 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4412. Min Act: -0.0000

Data Index: 77343 (C4 (Web Text))

Max Activating Token Index: 640

Text #18

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4347. Min Act: -0.0000

Data Index: 140463 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.6712. Min Range: -0.6712

Max Act: 0.4908. Min Act: -0.0000

Data Index: 553678 (C4 (Web Text))

Max Activating Token Index: 840