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

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

Neuron 2493 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6957. Min Act: -0.0000

Data Index: 816077 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6648. Min Act: -0.0000

Data Index: 459985 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.7531. Min Act: -0.0000

Data Index: 687332 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6452. Min Act: -0.0000

Data Index: 194011 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6631. Min Act: -0.0000

Data Index: 470952 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6842. Min Act: -0.0000

Data Index: 1028542 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6615. Min Act: -0.0000

Data Index: 4801 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6766. Min Act: -0.0000

Data Index: 1219058 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6416. Min Act: -0.0000

Data Index: 635317 (C4 (Web Text))

Max Activating Token Index: 568

Text #9

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6829. Min Act: -0.0000

Data Index: 215498 (C4 (Web Text))

Max Activating Token Index: 549

Text #10

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6540. Min Act: -0.0000

Data Index: 942396 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6334. Min Act: -0.0000

Data Index: 339455 (C4 (Web Text))

Max Activating Token Index: 498

Text #12

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1002079 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6404. Min Act: -0.0000

Data Index: 925777 (C4 (Web Text))

Max Activating Token Index: 513

Text #14

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6420. Min Act: -0.0000

Data Index: 805847 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1100342 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6554. Min Act: -0.0000

Data Index: 163365 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6309. Min Act: -0.0000

Data Index: 1335237 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.6071. Min Act: -0.0000

Data Index: 343445 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 0.7531. Min Range: -0.7531

Max Act: 0.5969. Min Act: -0.0000

Data Index: 659567 (C4 (Web Text))

Max Activating Token Index: 791