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

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

Neuron 721 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2502. Min Range: -2.2502

Max Act: 2.2502. Min Act: -0.0000

Data Index: 67557 (C4 (Web Text))

Max Activating Token Index: 181

Text #1

Max Range: 2.2502. Min Range: -2.2502

Max Act: 2.0432. Min Act: -0.0000

Data Index: 503129 (C4 (Web Text))

Max Activating Token Index: 858

Text #2

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.8976. Min Act: -0.0000

Data Index: 567072 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.8235. Min Act: -0.0000

Data Index: 190373 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.6302. Min Act: -0.0000

Data Index: 443324 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.4046. Min Act: -0.0000

Data Index: 600112 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.4478. Min Act: -0.0000

Data Index: 854147 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.3800. Min Act: -0.0000

Data Index: 896749 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.3883. Min Act: -0.0000

Data Index: 370879 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1645. Min Act: -0.0000

Data Index: 438308 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.2200. Min Act: -0.0000

Data Index: 316869 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1458. Min Act: -0.0000

Data Index: 1299743 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.2778. Min Act: -0.0000

Data Index: 690248 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1283. Min Act: -0.0000

Data Index: 504079 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.2468. Min Act: -0.0000

Data Index: 1037536 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1515. Min Act: -0.0000

Data Index: 601106 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1298. Min Act: -0.0000

Data Index: 524727 (C4 (Web Text))

Max Activating Token Index: 103

Text #17

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1258. Min Act: -0.0000

Data Index: 940410 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1215. Min Act: -0.0000

Data Index: 834160 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 2.2502. Min Range: -2.2502

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1568270 (Python Code)

Max Activating Token Index: 875