Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1654 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0001

Data Index: 411979 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0511. Min Act: -0.0001

Data Index: 494566 (C4 (Web Text))

Max Activating Token Index: 735

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0508. Min Act: -0.0001

Data Index: 382315 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1247202 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0490. Min Act: -0.0001

Data Index: 587565 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0521. Min Act: -0.0001

Data Index: 253364 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0512. Min Act: -0.0001

Data Index: 579937 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0508. Min Act: -0.0001

Data Index: 653781 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1011922 (C4 (Web Text))

Max Activating Token Index: 455

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0463. Min Act: -0.0001

Data Index: 282455 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0476. Min Act: -0.0001

Data Index: 112028 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0445. Min Act: -0.0001

Data Index: 1266580 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1104469 (C4 (Web Text))

Max Activating Token Index: 462

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0427. Min Act: -0.0001

Data Index: 403292 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0413. Min Act: -0.0001

Data Index: 106154 (C4 (Web Text))

Max Activating Token Index: 654

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0440. Min Act: -0.0001

Data Index: 1460983 (Python Code)

Max Activating Token Index: 307

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0431. Min Act: -0.0001

Data Index: 491194 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0461. Min Act: -0.0001

Data Index: 1201515 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0460. Min Act: -0.0001

Data Index: 381572 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0427. Min Act: -0.0001

Data Index: 1635845 (Python Code)

Max Activating Token Index: 134