Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1050 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0012. Min Range: -1.0012

Max Act: 1.0012. Min Act: -0.0000

Data Index: 1034098 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.9435. Min Act: -0.0000

Data Index: 694518 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8794. Min Act: -0.0000

Data Index: 82563 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8561. Min Act: -0.0000

Data Index: 836623 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8842. Min Act: -0.0000

Data Index: 431616 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8113. Min Act: -0.0000

Data Index: 1178934 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1331366 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8495. Min Act: -0.0000

Data Index: 525521 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8369. Min Act: -0.0000

Data Index: 935292 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8339. Min Act: -0.0000

Data Index: 102312 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.9181. Min Act: -0.0000

Data Index: 402365 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.8136. Min Act: -0.0000

Data Index: 94956 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7471. Min Act: -0.0000

Data Index: 302869 (C4 (Web Text))

Max Activating Token Index: 287

Text #13

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1337693 (C4 (Web Text))

Max Activating Token Index: 999

Text #14

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7781. Min Act: -0.0000

Data Index: 636283 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1418956 (Python Code)

Max Activating Token Index: 781

Text #16

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1117286 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7179. Min Act: -0.0000

Data Index: 324849 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7205. Min Act: -0.0000

Data Index: 944562 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 1.0012. Min Range: -1.0012

Max Act: 0.7326. Min Act: -0.0000

Data Index: 1004845 (C4 (Web Text))

Max Activating Token Index: 120