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

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

Neuron 2 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2049. Min Range: -5.2049

Max Act: 5.2049. Min Act: -0.0000

Data Index: 1346230 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.5007. Min Act: -0.0000

Data Index: 947710 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.3236. Min Act: -0.0000

Data Index: 855829 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 5.2049. Min Range: -5.2049

Max Act: 4.3436. Min Act: -0.0001

Data Index: 51780 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.5182. Min Act: -0.0001

Data Index: 1140273 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.5719. Min Act: -0.0000

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.7601. Min Act: -0.0000

Data Index: 688006 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.5752. Min Act: -0.0001

Data Index: 1051200 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.2687. Min Act: -0.0000

Data Index: 87929 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.0316. Min Act: -0.0000

Data Index: 1265408 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.2404. Min Act: -0.0000

Data Index: 809960 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.2366. Min Act: -0.0000

Data Index: 1059893 (C4 (Web Text))

Max Activating Token Index: 222

Text #12

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.2125. Min Act: -0.0000

Data Index: 1341436 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.1932. Min Act: -0.0000

Data Index: 896137 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.0609. Min Act: -0.0000

Data Index: 1069472 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.3292. Min Act: -0.0001

Data Index: 382749 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.1267. Min Act: -0.0000

Data Index: 635894 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.1297. Min Act: -0.0001

Data Index: 986191 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 5.2049. Min Range: -5.2049

Max Act: 2.8169. Min Act: -0.0000

Data Index: 747758 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 5.2049. Min Range: -5.2049

Max Act: 3.3845. Min Act: -0.0000

Data Index: 577644 (C4 (Web Text))

Max Activating Token Index: 219