Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1367 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0015. Min Act: -0.0006

Data Index: 37668 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0006. Min Act: -0.0005

Data Index: 1635595 (Python Code)

Max Activating Token Index: 571

Text #2

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0006. Min Act: -0.0006

Data Index: 1020273 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0005. Min Act: -0.0006

Data Index: 852498 (C4 (Web Text))

Max Activating Token Index: 517

Text #4

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0005. Min Act: -0.0006

Data Index: 1174664 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0005. Min Act: -0.0006

Data Index: 627978 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 118655 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0005

Data Index: 1555331 (Python Code)

Max Activating Token Index: 670

Text #8

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 677032 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0005

Data Index: 1457741 (Python Code)

Max Activating Token Index: 326

Text #10

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 923893 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 1220555 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 821342 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0005

Data Index: 1587599 (Python Code)

Max Activating Token Index: 380

Text #14

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 157106 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 416939 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0003. Min Act: -0.0006

Data Index: 691259 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 318905 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 674088 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.0015. Min Range: -0.0015

Max Act: 0.0004. Min Act: -0.0006

Data Index: 1209083 (C4 (Web Text))

Max Activating Token Index: 371