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

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

Neuron 2724 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: 1.0719. Min Range: -1.0719

Max Act: 0.9792. Min Act: -0.0001

Data Index: 1194070 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.0719. Min Range: -1.0719

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1142114 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 1.0719. Min Range: -1.0719

Max Act: 1.0692. Min Act: -0.0002

Data Index: 382941 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.0719. Min Range: -1.0719

Max Act: 1.0719. Min Act: -0.0001

Data Index: 512972 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 1.0719. Min Range: -1.0719

Max Act: 1.0350. Min Act: -0.0001

Data Index: 500955 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.9753. Min Act: -0.0001

Data Index: 1104323 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.9595. Min Act: -0.0001

Data Index: 1008223 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.9212. Min Act: -0.0002

Data Index: 765116 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.9790. Min Act: -0.0001

Data Index: 1168931 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8747. Min Act: -0.0002

Data Index: 145997 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8775. Min Act: -0.0002

Data Index: 483491 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8466. Min Act: -0.0001

Data Index: 56837 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8203. Min Act: -0.0001

Data Index: 499861 (C4 (Web Text))

Max Activating Token Index: 160

Text #13

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8956. Min Act: -0.0001

Data Index: 647317 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8419. Min Act: -0.0001

Data Index: 1245651 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.9172. Min Act: -0.0001

Data Index: 360267 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8184. Min Act: -0.0002

Data Index: 1312257 (C4 (Web Text))

Max Activating Token Index: 553

Text #17

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8761. Min Act: -0.0001

Data Index: 588271 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8528. Min Act: -0.0001

Data Index: 409444 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 1.0719. Min Range: -1.0719

Max Act: 0.8518. Min Act: -0.0001

Data Index: 814527 (C4 (Web Text))

Max Activating Token Index: 991