Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2266 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0191. Min Range: -1.0191

Max Act: 1.0191. Min Act: -0.0002

Data Index: 114692 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.9171. Min Act: -0.0001

Data Index: 1331388 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.9475. Min Act: -0.0001

Data Index: 862527 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.9231. Min Act: -0.0001

Data Index: 1319477 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.9922. Min Act: -0.0002

Data Index: 992237 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8681. Min Act: -0.0002

Data Index: 1244565 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8309. Min Act: -0.0002

Data Index: 1332918 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8284. Min Act: -0.0002

Data Index: 1322107 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8277. Min Act: -0.0001

Data Index: 1021513 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8162. Min Act: -0.0001

Data Index: 940091 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8365. Min Act: -0.0001

Data Index: 212778 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7758. Min Act: -0.0002

Data Index: 556374 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7759. Min Act: -0.0001

Data Index: 950502 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7333. Min Act: -0.0002

Data Index: 993581 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7919. Min Act: -0.0001

Data Index: 1234853 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7907. Min Act: -0.0002

Data Index: 661862 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7684. Min Act: -0.0001

Data Index: 1115570 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.7904. Min Act: -0.0002

Data Index: 935434 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8446. Min Act: -0.0001

Data Index: 856150 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 1.0191. Min Range: -1.0191

Max Act: 0.8323. Min Act: -0.0001

Data Index: 192229 (C4 (Web Text))

Max Activating Token Index: 808