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

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

Neuron 4479 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.3122. Min Act: -0.0001

Data Index: 744305 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.3619. Min Act: -0.0001

Data Index: 510577 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2342. Min Act: -0.0001

Data Index: 1347143 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2320. Min Act: -0.0001

Data Index: 907342 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2239. Min Act: -0.0001

Data Index: 86850 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.1747. Min Act: -0.0001

Data Index: 131400 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2194. Min Act: -0.0001

Data Index: 613514 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2489. Min Act: -0.0001

Data Index: 1349681 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.0031. Min Act: -0.0001

Data Index: 1040874 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.1406. Min Act: -0.0001

Data Index: 772960 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2256. Min Act: -0.0001

Data Index: 1332756 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.1860. Min Act: -0.0001

Data Index: 252550 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2076. Min Act: -0.0001

Data Index: 842276 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.1744. Min Act: -0.0001

Data Index: 237191 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.1612. Min Act: -0.0001

Data Index: 1199232 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.1572. Min Act: -0.0001

Data Index: 152286 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.0915. Min Act: -0.0001

Data Index: 950044 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.3619. Min Range: -1.3619

Max Act: 0.9964. Min Act: -0.0001

Data Index: 1024430 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.2252. Min Act: -0.0001

Data Index: 984847 (C4 (Web Text))

Max Activating Token Index: 884

Text #19

Max Range: 1.3619. Min Range: -1.3619

Max Act: 1.1472. Min Act: -0.0001

Data Index: 926417 (C4 (Web Text))

Max Activating Token Index: 736