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

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

Neuron 471 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9391. Min Act: -0.0001

Data Index: 1299525 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1033655 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8929. Min Act: -0.0001

Data Index: 298283 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8026. Min Act: -0.0001

Data Index: 952886 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8402. Min Act: -0.0001

Data Index: 23238 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8913. Min Act: -0.0001

Data Index: 1022472 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8545. Min Act: -0.0001

Data Index: 300725 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9015. Min Act: -0.0001

Data Index: 957437 (C4 (Web Text))

Max Activating Token Index: 459

Text #8

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.9287. Min Act: -0.0001

Data Index: 148053 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8010. Min Act: -0.0001

Data Index: 1310988 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.8271. Min Act: -0.0001

Data Index: 986718 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.6904. Min Act: -0.0001

Data Index: 426650 (C4 (Web Text))

Max Activating Token Index: 116

Text #12

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1059393 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7823. Min Act: -0.0001

Data Index: 924148 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.6986. Min Act: -0.0001

Data Index: 1099320 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7905. Min Act: -0.0001

Data Index: 1211868 (C4 (Web Text))

Max Activating Token Index: 738

Text #16

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7534. Min Act: -0.0001

Data Index: 641668 (C4 (Web Text))

Max Activating Token Index: 609

Text #17

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.6467. Min Act: -0.0001

Data Index: 1210925 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7296. Min Act: -0.0001

Data Index: 189510 (C4 (Web Text))

Max Activating Token Index: 267

Text #19

Max Range: 0.9556. Min Range: -0.9556

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1462644 (Python Code)

Max Activating Token Index: 562