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

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

Neuron 4100 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7365. Min Range: -2.7365

Max Act: 2.7365. Min Act: -0.0000

Data Index: 236134 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 2.7365. Min Range: -2.7365

Max Act: 2.5009. Min Act: -0.0001

Data Index: 885884 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 2.7365. Min Range: -2.7365

Max Act: 2.2579. Min Act: -0.0001

Data Index: 1013830 (C4 (Web Text))

Max Activating Token Index: 1005

Text #3

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.9014. Min Act: -0.0000

Data Index: 576068 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 2.7365. Min Range: -2.7365

Max Act: 2.1874. Min Act: -0.0000

Data Index: 807365 (C4 (Web Text))

Max Activating Token Index: 49

Text #5

Max Range: 2.7365. Min Range: -2.7365

Max Act: 2.0870. Min Act: -0.0000

Data Index: 980206 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 2.7365. Min Range: -2.7365

Max Act: 2.0722. Min Act: -0.0000

Data Index: 462860 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.8504. Min Act: -0.0001

Data Index: 335660 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 2.7365. Min Range: -2.7365

Max Act: 2.0382. Min Act: -0.0000

Data Index: 1028674 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.9073. Min Act: -0.0000

Data Index: 1080405 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.8905. Min Act: -0.0000

Data Index: 184550 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.7495. Min Act: -0.0000

Data Index: 463439 (C4 (Web Text))

Max Activating Token Index: 969

Text #12

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.9927. Min Act: -0.0000

Data Index: 1300673 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.6771. Min Act: -0.0000

Data Index: 539940 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.7608. Min Act: -0.0000

Data Index: 502915 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.9083. Min Act: -0.0000

Data Index: 1212192 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.9492. Min Act: -0.0001

Data Index: 911070 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.7288. Min Act: -0.0001

Data Index: 805786 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.7708. Min Act: -0.0001

Data Index: 584402 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 2.7365. Min Range: -2.7365

Max Act: 1.9091. Min Act: -0.0000

Data Index: 504248 (C4 (Web Text))

Max Activating Token Index: 627