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

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

Neuron 652 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: 1.4393. Min Range: -1.4393

Max Act: 1.4393. Min Act: -0.0000

Data Index: 615890 (C4 (Web Text))

Max Activating Token Index: 517

Text #1

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.3954. Min Act: -0.0000

Data Index: 339447 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.3525. Min Act: -0.0000

Data Index: 981521 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2124. Min Act: -0.0000

Data Index: 142272 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.2124. Min Act: -0.0000

Data Index: 810886 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1044809 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1608. Min Act: -0.0000

Data Index: 320398 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1696. Min Act: -0.0000

Data Index: 60613 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1289. Min Act: -0.0000

Data Index: 19473 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.1208. Min Act: -0.0000

Data Index: 28614 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0796. Min Act: -0.0000

Data Index: 611315 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0723. Min Act: -0.0000

Data Index: 1046596 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0858. Min Act: -0.0000

Data Index: 1108547 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0855. Min Act: -0.0000

Data Index: 289858 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0966. Min Act: -0.0000

Data Index: 1338809 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0612. Min Act: -0.0000

Data Index: 418905 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0185. Min Act: -0.0000

Data Index: 1328689 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0123. Min Act: -0.0000

Data Index: 525264 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 1.4393. Min Range: -1.4393

Max Act: 0.9583. Min Act: -0.0000

Data Index: 1284485 (C4 (Web Text))

Max Activating Token Index: 633

Text #19

Max Range: 1.4393. Min Range: -1.4393

Max Act: 1.0466. Min Act: -0.0000

Data Index: 297287 (C4 (Web Text))

Max Activating Token Index: 351