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

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

Neuron 4568 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: 1.6009. Min Range: -1.6009

Max Act: 1.6009. Min Act: -0.0001

Data Index: 1377789 (Python Code)

Max Activating Token Index: 771

Text #1

Max Range: 1.6009. Min Range: -1.6009

Max Act: 1.2315. Min Act: -0.0000

Data Index: 1646683 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 1.6009. Min Range: -1.6009

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1363181 (Python Code)

Max Activating Token Index: 700

Text #3

Max Range: 1.6009. Min Range: -1.6009

Max Act: 1.0045. Min Act: -0.0000

Data Index: 1588369 (Python Code)

Max Activating Token Index: 599

Text #4

Max Range: 1.6009. Min Range: -1.6009

Max Act: 1.0167. Min Act: -0.0000

Data Index: 1387281 (Python Code)

Max Activating Token Index: 555

Text #5

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.9577. Min Act: -0.0000

Data Index: 1073194 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.9528. Min Act: -0.0000

Data Index: 1618859 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1544852 (Python Code)

Max Activating Token Index: 800

Text #8

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1192544 (C4 (Web Text))

Max Activating Token Index: 948

Text #9

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.9038. Min Act: -0.0000

Data Index: 1507500 (Python Code)

Max Activating Token Index: 509

Text #10

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1636965 (Python Code)

Max Activating Token Index: 504

Text #11

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1525497 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8931. Min Act: 0.0000

Data Index: 477375 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8675. Min Act: -0.0000

Data Index: 1596128 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8581. Min Act: -0.0000

Data Index: 172111 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8641. Min Act: -0.0000

Data Index: 1518006 (Python Code)

Max Activating Token Index: 309

Text #16

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8556. Min Act: -0.0000

Data Index: 242311 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8318. Min Act: -0.0000

Data Index: 1629462 (Python Code)

Max Activating Token Index: 435

Text #18

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1450880 (Python Code)

Max Activating Token Index: 418

Text #19

Max Range: 1.6009. Min Range: -1.6009

Max Act: 0.8380. Min Act: -0.0000

Data Index: 1458964 (Python Code)

Max Activating Token Index: 285