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

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

Neuron 4915 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: 2.2492. Min Range: -2.2492

Max Act: 2.1243. Min Act: -0.0000

Data Index: 705968 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 2.2492. Min Range: -2.2492

Max Act: 2.0416. Min Act: -0.0000

Data Index: 746095 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 2.2492. Min Range: -2.2492

Max Act: 2.2492. Min Act: -0.0000

Data Index: 964758 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 2.2492. Min Range: -2.2492

Max Act: 2.0662. Min Act: -0.0000

Data Index: 15273 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.9870. Min Act: -0.0000

Data Index: 1176266 (C4 (Web Text))

Max Activating Token Index: 966

Text #5

Max Range: 2.2492. Min Range: -2.2492

Max Act: 2.0825. Min Act: -0.0000

Data Index: 1169059 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 2.2492. Min Range: -2.2492

Max Act: 2.0635. Min Act: -0.0000

Data Index: 208489 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.9528. Min Act: -0.0000

Data Index: 905345 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.9419. Min Act: -0.0000

Data Index: 63616 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 2.2492. Min Range: -2.2492

Max Act: 2.0505. Min Act: -0.0000

Data Index: 974455 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.7914. Min Act: -0.0000

Data Index: 891144 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.8819. Min Act: -0.0000

Data Index: 304196 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.8101. Min Act: -0.0000

Data Index: 116909 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.8647. Min Act: -0.0000

Data Index: 777653 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.7604. Min Act: -0.0000

Data Index: 1129720 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.7642. Min Act: -0.0000

Data Index: 409614 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.8472. Min Act: -0.0000

Data Index: 509472 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.8494. Min Act: -0.0000

Data Index: 800681 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.7528. Min Act: -0.0000

Data Index: 860891 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 2.2492. Min Range: -2.2492

Max Act: 1.8341. Min Act: -0.0000

Data Index: 35491 (C4 (Web Text))

Max Activating Token Index: 287