Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2885 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3245. Min Act: -0.0001

Data Index: 633979 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3302. Min Act: -0.0001

Data Index: 706648 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3245. Min Act: -0.0001

Data Index: 784386 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3029. Min Act: -0.0001

Data Index: 1481423 (Python Code)

Max Activating Token Index: 837

Text #4

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1513876 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1484631 (Python Code)

Max Activating Token Index: 773

Text #6

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2768. Min Act: -0.0001

Data Index: 1575571 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2998. Min Act: -0.0001

Data Index: 775389 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.3089. Min Act: -0.0001

Data Index: 1411506 (Python Code)

Max Activating Token Index: 802

Text #9

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2704. Min Act: -0.0001

Data Index: 246823 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2710. Min Act: -0.0001

Data Index: 1223707 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1267355 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1494862 (Python Code)

Max Activating Token Index: 989

Text #13

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2869. Min Act: -0.0001

Data Index: 706587 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2769. Min Act: -0.0001

Data Index: 60764 (C4 (Web Text))

Max Activating Token Index: 458

Text #15

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2508. Min Act: -0.0001

Data Index: 377690 (C4 (Web Text))

Max Activating Token Index: 257

Text #16

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2493. Min Act: -0.0001

Data Index: 355452 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2958. Min Act: -0.0001

Data Index: 673760 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2837. Min Act: -0.0001

Data Index: 542959 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.3302. Min Range: -0.3302

Max Act: 0.2373. Min Act: -0.0001

Data Index: 23444 (C4 (Web Text))

Max Activating Token Index: 572