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

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

Neuron 2114 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: 4.8603. Min Range: -4.8603

Max Act: 4.8603. Min Act: -0.0000

Data Index: 375600 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.6849. Min Act: -0.0000

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.5456. Min Act: -0.0000

Data Index: 1034774 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.6427. Min Act: -0.0000

Data Index: 1126940 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.3857. Min Act: -0.0000

Data Index: 527960 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.7032. Min Act: -0.0000

Data Index: 604838 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.4092. Min Act: -0.0000

Data Index: 788683 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.2244. Min Act: -0.0000

Data Index: 1318766 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.4656. Min Act: -0.0000

Data Index: 1265490 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.3513. Min Act: -0.0000

Data Index: 352523 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.4441. Min Act: -0.0000

Data Index: 969315 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.1954. Min Act: -0.0000

Data Index: 384084 (C4 (Web Text))

Max Activating Token Index: 972

Text #12

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.3012. Min Act: -0.0000

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 4.8603. Min Range: -4.8603

Max Act: 1.9675. Min Act: -0.0000

Data Index: 1234331 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.2502. Min Act: -0.0000

Data Index: 832405 (C4 (Web Text))

Max Activating Token Index: 698

Text #15

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.2550. Min Act: -0.0000

Data Index: 1482780 (Python Code)

Max Activating Token Index: 228

Text #16

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.2268. Min Act: -0.0000

Data Index: 933813 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.2096. Min Act: -0.0000

Data Index: 1466455 (Python Code)

Max Activating Token Index: 230

Text #18

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.3004. Min Act: -0.0000

Data Index: 136259 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 4.8603. Min Range: -4.8603

Max Act: 2.1632. Min Act: -0.0000

Data Index: 651630 (C4 (Web Text))

Max Activating Token Index: 352