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

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

Neuron 4595 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1017. Min Range: -7.1017

Max Act: 7.1017. Min Act: -0.0000

Data Index: 617251 (C4 (Web Text))

Max Activating Token Index: 217

Text #1

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.6315. Min Act: -0.0000

Data Index: 943413 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.7387. Min Act: -0.0000

Data Index: 512310 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.3742. Min Act: -0.0000

Data Index: 1085673 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.5408. Min Act: -0.0000

Data Index: 916696 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.2657. Min Act: -0.0000

Data Index: 794387 (C4 (Web Text))

Max Activating Token Index: 319

Text #6

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.3498. Min Act: -0.0000

Data Index: 131743 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.0395. Min Act: -0.0000

Data Index: 545868 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 7.1017. Min Range: -7.1017

Max Act: 6.0223. Min Act: -0.0000

Data Index: 706499 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.9871. Min Act: -0.0000

Data Index: 1238630 (C4 (Web Text))

Max Activating Token Index: 303

Text #10

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.5716. Min Act: -0.0000

Data Index: 37840 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.7547. Min Act: -0.0000

Data Index: 762634 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.5761. Min Act: -0.0000

Data Index: 406449 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.5481. Min Act: -0.0000

Data Index: 512852 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.5786. Min Act: -0.0000

Data Index: 1090579 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.1826. Min Act: -0.0000

Data Index: 336207 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.5656. Min Act: -0.0000

Data Index: 998800 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.2995. Min Act: -0.0000

Data Index: 739770 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.2614. Min Act: -0.0000

Data Index: 1215389 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 7.1017. Min Range: -7.1017

Max Act: 5.4156. Min Act: -0.0000

Data Index: 1247471 (C4 (Web Text))

Max Activating Token Index: 703