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

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

Neuron 2825 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.5582. Min Act: -0.0000

Data Index: 746089 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.5398. Min Act: -0.0000

Data Index: 653944 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.4982. Min Act: -0.0000

Data Index: 113558 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3953. Min Act: -0.0000

Data Index: 144755 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3834. Min Act: -0.0000

Data Index: 555159 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3719. Min Act: -0.0000

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3501. Min Act: -0.0000

Data Index: 1164806 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1008221 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3200. Min Act: -0.0000

Data Index: 561409 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3063. Min Act: -0.0000

Data Index: 284880 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3277. Min Act: -0.0000

Data Index: 750753 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1186531 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2942. Min Act: -0.0000

Data Index: 827794 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2552. Min Act: -0.0000

Data Index: 358596 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2977. Min Act: -0.0000

Data Index: 664185 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1032536 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2750. Min Act: -0.0000

Data Index: 594348 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2885. Min Act: -0.0000

Data Index: 143138 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2561. Min Act: -0.0000

Data Index: 170161 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.5582. Min Range: -0.5582

Max Act: 0.2803. Min Act: -0.0000

Data Index: 1204303 (C4 (Web Text))

Max Activating Token Index: 268