Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1034 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0601. Min Act: -0.0004

Data Index: 343836 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0580. Min Act: -0.0004

Data Index: 1348018 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0590. Min Act: -0.0004

Data Index: 256390 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0613. Min Act: -0.0004

Data Index: 446025 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0582. Min Act: -0.0004

Data Index: 1165047 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0607. Min Act: -0.0004

Data Index: 280267 (C4 (Web Text))

Max Activating Token Index: 145

Text #6

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0578. Min Act: -0.0004

Data Index: 199584 (C4 (Web Text))

Max Activating Token Index: 508

Text #7

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0600. Min Act: -0.0004

Data Index: 980144 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0567. Min Act: -0.0004

Data Index: 764156 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0588. Min Act: -0.0004

Data Index: 1270045 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0585. Min Act: -0.0004

Data Index: 688786 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0563. Min Act: -0.0004

Data Index: 1101863 (C4 (Web Text))

Max Activating Token Index: 209

Text #12

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0582. Min Act: -0.0004

Data Index: 318546 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0576. Min Act: -0.0004

Data Index: 1300038 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0582. Min Act: -0.0004

Data Index: 492212 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0579. Min Act: -0.0004

Data Index: 593966 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0609. Min Act: -0.0004

Data Index: 963395 (C4 (Web Text))

Max Activating Token Index: 328

Text #17

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0577. Min Act: -0.0004

Data Index: 179261 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0555. Min Act: -0.0004

Data Index: 962320 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.0613. Min Range: -0.0613

Max Act: 0.0576. Min Act: -0.0004

Data Index: 362204 (C4 (Web Text))

Max Activating Token Index: 887