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

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

Neuron 4542 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.9179. Min Act: -0.0000

Data Index: 1344811 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.7777. Min Act: -0.0000

Data Index: 749 (C4 (Web Text))

Max Activating Token Index: 451

Text #2

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.5010. Min Act: -0.0000

Data Index: 1013765 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.4951. Min Act: -0.0000

Data Index: 61580 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.4335. Min Act: -0.0000

Data Index: 189528 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.2818. Min Act: -0.0000

Data Index: 725316 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.2558. Min Act: -0.0000

Data Index: 388902 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.2395. Min Act: -0.0000

Data Index: 141255 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.2054. Min Act: -0.0000

Data Index: 398462 (C4 (Web Text))

Max Activating Token Index: 655

Text #9

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.2068. Min Act: -0.0000

Data Index: 514284 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.3213. Min Act: -0.0000

Data Index: 657494 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.1424. Min Act: -0.0000

Data Index: 465538 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 2.9179. Min Range: -2.9179

Max Act: 1.9371. Min Act: -0.0000

Data Index: 1175307 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.0038. Min Act: -0.0000

Data Index: 1071712 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 2.9179. Min Range: -2.9179

Max Act: 2.1023. Min Act: -0.0000

Data Index: 1042474 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 2.9179. Min Range: -2.9179

Max Act: 1.9775. Min Act: -0.0000

Data Index: 630116 (C4 (Web Text))

Max Activating Token Index: 395

Text #16

Max Range: 2.9179. Min Range: -2.9179

Max Act: 1.8622. Min Act: -0.0000

Data Index: 673203 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 2.9179. Min Range: -2.9179

Max Act: 1.9705. Min Act: -0.0000

Data Index: 510475 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 2.9179. Min Range: -2.9179

Max Act: 1.8622. Min Act: -0.0000

Data Index: 616714 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 2.9179. Min Range: -2.9179

Max Act: 1.8473. Min Act: -0.0000

Data Index: 364939 (C4 (Web Text))

Max Activating Token Index: 125