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

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

Neuron 215 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.2163. Min Act: -0.0000

Data Index: 233832 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.4744. Min Act: -0.0000

Data Index: 1637205 (Python Code)

Max Activating Token Index: 50

Text #2

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.2783. Min Act: -0.0000

Data Index: 1023838 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.2735. Min Act: -0.0000

Data Index: 1357009 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.2223. Min Act: -0.0000

Data Index: 1637537 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.3099. Min Act: -0.0001

Data Index: 1638521 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.0509. Min Act: -0.0000

Data Index: 234271 (C4 (Web Text))

Max Activating Token Index: 911

Text #7

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.0594. Min Act: -0.0000

Data Index: 99850 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.0542. Min Act: -0.0000

Data Index: 699784 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.0581. Min Act: -0.0000

Data Index: 1285275 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.1457. Min Act: -0.0001

Data Index: 1645679 (Python Code)

Max Activating Token Index: 363

Text #11

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.1262. Min Act: -0.0000

Data Index: 1617195 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.1251. Min Act: -0.0000

Data Index: 429643 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.1116. Min Act: -0.0000

Data Index: 75195 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.1067. Min Act: -0.0000

Data Index: 549547 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.1031. Min Act: -0.0000

Data Index: 995094 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.1051. Min Act: -0.0000

Data Index: 1441721 (Python Code)

Max Activating Token Index: 369

Text #17

Max Range: 2.4744. Min Range: -2.4744

Max Act: 2.0951. Min Act: -0.0000

Data Index: 1061429 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9450. Min Act: -0.0000

Data Index: 1220358 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 2.4744. Min Range: -2.4744

Max Act: 1.9433. Min Act: -0.0000

Data Index: 1508604 (Python Code)

Max Activating Token Index: 947