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

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

Neuron 4825 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2250. Min Range: -1.2250

Max Act: 1.2250. Min Act: 0.0000

Data Index: 1345099 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.2250. Min Range: -1.2250

Max Act: 1.0467. Min Act: -0.0000

Data Index: 393543 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.2250. Min Range: -1.2250

Max Act: 1.0631. Min Act: -0.0000

Data Index: 44012 (C4 (Web Text))

Max Activating Token Index: 41

Text #3

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.9595. Min Act: -0.0000

Data Index: 1172069 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.9616. Min Act: -0.0000

Data Index: 178817 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.9630. Min Act: 0.0000

Data Index: 1020254 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.9525. Min Act: -0.0000

Data Index: 1236802 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1023087 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.8718. Min Act: -0.0000

Data Index: 302238 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.8139. Min Act: 0.0000

Data Index: 779809 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.9027. Min Act: -0.0000

Data Index: 41776 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.8528. Min Act: 0.0000

Data Index: 1341655 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.8448. Min Act: -0.0000

Data Index: 735712 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.7890. Min Act: -0.0000

Data Index: 754232 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.8253. Min Act: -0.0000

Data Index: 1047508 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.7797. Min Act: -0.0000

Data Index: 843202 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.7698. Min Act: -0.0000

Data Index: 479688 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.7680. Min Act: -0.0000

Data Index: 815432 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.7901. Min Act: -0.0000

Data Index: 88873 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 1.2250. Min Range: -1.2250

Max Act: 0.7859. Min Act: -0.0000

Data Index: 1285272 (C4 (Web Text))

Max Activating Token Index: 202