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

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

Neuron 5114 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: 3.0832. Min Range: -3.0832

Max Act: 3.0672. Min Act: -0.0001

Data Index: 138625 (C4 (Web Text))

Max Activating Token Index: 692

Text #1

Max Range: 3.0832. Min Range: -3.0832

Max Act: 3.0832. Min Act: -0.0001

Data Index: 1080334 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.7406. Min Act: -0.0001

Data Index: 885246 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.9248. Min Act: -0.0001

Data Index: 1161086 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.7846. Min Act: -0.0001

Data Index: 1056435 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.8398. Min Act: -0.0001

Data Index: 286865 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.9681. Min Act: -0.0001

Data Index: 136136 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.7025. Min Act: -0.0001

Data Index: 642266 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.4528. Min Act: -0.0001

Data Index: 1347756 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.3937. Min Act: -0.0001

Data Index: 1312563 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.4164. Min Act: -0.0001

Data Index: 834980 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.4094. Min Act: -0.0001

Data Index: 986054 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.4169. Min Act: -0.0001

Data Index: 64401 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.2457. Min Act: -0.0001

Data Index: 227823 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.4563. Min Act: -0.0001

Data Index: 1266350 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.2263. Min Act: -0.0001

Data Index: 118845 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.3373. Min Act: -0.0001

Data Index: 166129 (C4 (Web Text))

Max Activating Token Index: 747

Text #17

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.4442. Min Act: -0.0001

Data Index: 622534 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.5348. Min Act: -0.0001

Data Index: 395399 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 3.0832. Min Range: -3.0832

Max Act: 2.3883. Min Act: -0.0001

Data Index: 72984 (C4 (Web Text))

Max Activating Token Index: 547