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

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

Neuron 2153 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0232. Min Range: -1.0232

Max Act: 1.0232. Min Act: -0.0000

Data Index: 755235 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.9309. Min Act: -0.0000

Data Index: 38062 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.9191. Min Act: -0.0000

Data Index: 221761 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8693. Min Act: -0.0000

Data Index: 642477 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8832. Min Act: -0.0000

Data Index: 115219 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.9083. Min Act: -0.0000

Data Index: 735027 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1050675 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1155497 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8451. Min Act: -0.0000

Data Index: 214886 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8547. Min Act: -0.0000

Data Index: 1080400 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8354. Min Act: -0.0000

Data Index: 713355 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8457. Min Act: -0.0000

Data Index: 393058 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7500. Min Act: -0.0000

Data Index: 53108 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8257. Min Act: -0.0000

Data Index: 730600 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.8064. Min Act: -0.0000

Data Index: 865915 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7625. Min Act: -0.0000

Data Index: 200207 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7913. Min Act: -0.0000

Data Index: 1024373 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1064521 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7443. Min Act: -0.0000

Data Index: 118654 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 1.0232. Min Range: -1.0232

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1124256 (C4 (Web Text))

Max Activating Token Index: 370