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

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

Neuron 4808 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.4321. Min Act: -0.0001

Data Index: 1134847 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.4615. Min Act: -0.0001

Data Index: 255293 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.3280. Min Act: -0.0001

Data Index: 1314706 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.3525. Min Act: -0.0001

Data Index: 480037 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.3078. Min Act: -0.0001

Data Index: 447285 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2386. Min Act: -0.0001

Data Index: 1013354 (C4 (Web Text))

Max Activating Token Index: 941

Text #6

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.3458. Min Act: -0.0001

Data Index: 1212602 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2869. Min Act: -0.0001

Data Index: 749065 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2573. Min Act: -0.0001

Data Index: 1345101 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2728. Min Act: -0.0001

Data Index: 1186826 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2500. Min Act: -0.0001

Data Index: 1500150 (Python Code)

Max Activating Token Index: 579

Text #11

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2374. Min Act: -0.0001

Data Index: 220797 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.1540. Min Act: -0.0001

Data Index: 538120 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2151. Min Act: -0.0001

Data Index: 138987 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2094. Min Act: -0.0001

Data Index: 819678 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.1941. Min Act: -0.0001

Data Index: 1329759 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2223. Min Act: -0.0001

Data Index: 1150136 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2121. Min Act: -0.0001

Data Index: 761639 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2121. Min Act: -0.0001

Data Index: 1224220 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 1.4615. Min Range: -1.4615

Max Act: 1.2121. Min Act: -0.0001

Data Index: 1134279 (C4 (Web Text))

Max Activating Token Index: 2