Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3471 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0020. Min Act: -0.0002

Data Index: 683915 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0014. Min Act: -0.0003

Data Index: 684939 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0014. Min Act: -0.0002

Data Index: 1240273 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0013. Min Act: -0.0002

Data Index: 547890 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0012. Min Act: -0.0003

Data Index: 391759 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0012. Min Act: -0.0003

Data Index: 45078 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0012. Min Act: -0.0002

Data Index: 592346 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0012. Min Act: -0.0002

Data Index: 1639560 (Python Code)

Max Activating Token Index: 458

Text #8

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0012. Min Act: -0.0002

Data Index: 219345 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0011. Min Act: -0.0002

Data Index: 592204 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0010. Min Act: -0.0003

Data Index: 677607 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0010. Min Act: -0.0002

Data Index: 1522410 (Python Code)

Max Activating Token Index: 692

Text #12

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 652790 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1545577 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 652418 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 589423 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1309706 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 255335 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 1331018 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.0020. Min Range: -0.0020

Max Act: 0.0009. Min Act: -0.0002

Data Index: 45436 (C4 (Web Text))

Max Activating Token Index: 389