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

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

Neuron 2986 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4594. Min Range: -3.4594

Max Act: 3.4594. Min Act: -0.0000

Data Index: 221028 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 3.4594. Min Range: -3.4594

Max Act: 3.1448. Min Act: -0.0000

Data Index: 802588 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 3.4594. Min Range: -3.4594

Max Act: 3.1346. Min Act: -0.0000

Data Index: 1093336 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.9752. Min Act: -0.0000

Data Index: 1656850 (Python Code)

Max Activating Token Index: 136

Text #4

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.7887. Min Act: -0.0000

Data Index: 120996 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.7547. Min Act: -0.0000

Data Index: 428548 (C4 (Web Text))

Max Activating Token Index: 462

Text #6

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.8343. Min Act: -0.0000

Data Index: 14295 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.5570. Min Act: -0.0000

Data Index: 1624251 (Python Code)

Max Activating Token Index: 525

Text #8

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.5591. Min Act: -0.0000

Data Index: 1599555 (Python Code)

Max Activating Token Index: 656

Text #9

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.6509. Min Act: -0.0000

Data Index: 1373534 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.4858. Min Act: -0.0000

Data Index: 980345 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.5213. Min Act: -0.0000

Data Index: 1377120 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.4678. Min Act: -0.0000

Data Index: 1130079 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.3380. Min Act: -0.0000

Data Index: 1181014 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.2828. Min Act: -0.0000

Data Index: 1590373 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.2774. Min Act: -0.0000

Data Index: 963531 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.1384. Min Act: -0.0000

Data Index: 966742 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.2060. Min Act: -0.0000

Data Index: 942875 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.1930. Min Act: -0.0000

Data Index: 49409 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 3.4594. Min Range: -3.4594

Max Act: 2.1954. Min Act: -0.0000

Data Index: 797344 (C4 (Web Text))

Max Activating Token Index: 553