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

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

Neuron 3038 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: 0.5759. Min Range: -0.5759

Max Act: 0.5759. Min Act: -0.0000

Data Index: 83257 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5728. Min Act: -0.0000

Data Index: 1138072 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4797. Min Act: -0.0000

Data Index: 1049497 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4665. Min Act: -0.0000

Data Index: 379784 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1333925 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4427. Min Act: -0.0000

Data Index: 57198 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4301. Min Act: -0.0000

Data Index: 567433 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1230848 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3947. Min Act: -0.0000

Data Index: 241732 (C4 (Web Text))

Max Activating Token Index: 784

Text #9

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3771. Min Act: -0.0000

Data Index: 332715 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4019. Min Act: -0.0000

Data Index: 744681 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3761. Min Act: -0.0000

Data Index: 1008109 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4334. Min Act: -0.0000

Data Index: 976055 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3870. Min Act: -0.0000

Data Index: 808388 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3629. Min Act: -0.0000

Data Index: 1351018 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3838. Min Act: -0.0000

Data Index: 104541 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3804. Min Act: -0.0000

Data Index: 1035270 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3379. Min Act: -0.0000

Data Index: 115890 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1058103 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3324. Min Act: -0.0000

Data Index: 653775 (C4 (Web Text))

Max Activating Token Index: 744