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

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

Neuron 18 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: 1.6875. Min Range: -1.6875

Max Act: 1.6875. Min Act: -0.0001

Data Index: 700235 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.6338. Min Act: -0.0001

Data Index: 796302 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.5581. Min Act: -0.0001

Data Index: 729593 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3485. Min Act: -0.0001

Data Index: 1147180 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.4961. Min Act: -0.0001

Data Index: 425859 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3984. Min Act: -0.0001

Data Index: 1022929 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.4894. Min Act: -0.0001

Data Index: 1008179 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3442. Min Act: -0.0001

Data Index: 1187027 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3563. Min Act: -0.0001

Data Index: 1320980 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2861. Min Act: -0.0001

Data Index: 991675 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3041. Min Act: -0.0001

Data Index: 86837 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.3402. Min Act: -0.0001

Data Index: 1268429 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.1516. Min Act: -0.0001

Data Index: 699377 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2848. Min Act: -0.0001

Data Index: 932137 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.1509. Min Act: -0.0001

Data Index: 741890 (C4 (Web Text))

Max Activating Token Index: 264

Text #15

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.2058. Min Act: -0.0001

Data Index: 73126 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.1049. Min Act: -0.0001

Data Index: 189738 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.1215. Min Act: -0.0001

Data Index: 1236061 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.0410. Min Act: -0.0001

Data Index: 676137 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 1.6875. Min Range: -1.6875

Max Act: 1.1214. Min Act: -0.0001

Data Index: 214321 (C4 (Web Text))

Max Activating Token Index: 711