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

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

Neuron 3720 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: 1.1610. Min Range: -1.1610

Max Act: 1.1610. Min Act: -0.0001

Data Index: 1006802 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8795. Min Act: -0.0001

Data Index: 403071 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.9265. Min Act: -0.0001

Data Index: 600455 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8145. Min Act: -0.0001

Data Index: 63786 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8315. Min Act: -0.0001

Data Index: 77814 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8550. Min Act: -0.0001

Data Index: 487588 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8053. Min Act: -0.0001

Data Index: 724575 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8028. Min Act: -0.0001

Data Index: 1029307 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8253. Min Act: -0.0001

Data Index: 401315 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8876. Min Act: -0.0001

Data Index: 754507 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8512. Min Act: -0.0001

Data Index: 598132 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8776. Min Act: -0.0001

Data Index: 647493 (C4 (Web Text))

Max Activating Token Index: 994

Text #12

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8236. Min Act: -0.0001

Data Index: 292246 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8185. Min Act: -0.0001

Data Index: 130931 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8204. Min Act: -0.0001

Data Index: 1060697 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7405. Min Act: -0.0001

Data Index: 954538 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8636. Min Act: -0.0001

Data Index: 829036 (C4 (Web Text))

Max Activating Token Index: 855

Text #17

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8132. Min Act: -0.0001

Data Index: 1132216 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.7985. Min Act: -0.0001

Data Index: 35993 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.1610. Min Range: -1.1610

Max Act: 0.8718. Min Act: -0.0001

Data Index: 22570 (C4 (Web Text))

Max Activating Token Index: 731