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

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

Neuron 1043 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2311. Min Act: -0.0001

Data Index: 1160137 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2015. Min Act: -0.0001

Data Index: 259985 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2015. Min Act: -0.0000

Data Index: 454891 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1949. Min Act: -0.0001

Data Index: 661932 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1778. Min Act: -0.0001

Data Index: 169002 (C4 (Web Text))

Max Activating Token Index: 567

Text #5

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2120. Min Act: -0.0001

Data Index: 1022737 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.2357. Min Act: -0.0001

Data Index: 1114157 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1075435 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1618. Min Act: -0.0001

Data Index: 505606 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1690. Min Act: -0.0001

Data Index: 207478 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1604. Min Act: -0.0000

Data Index: 39605 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1631. Min Act: -0.0001

Data Index: 85267 (C4 (Web Text))

Max Activating Token Index: 482

Text #12

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1575. Min Act: -0.0001

Data Index: 368438 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1504. Min Act: -0.0001

Data Index: 885512 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1471486 (Python Code)

Max Activating Token Index: 524

Text #15

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1680. Min Act: -0.0001

Data Index: 38591 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1454. Min Act: -0.0001

Data Index: 1544225 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1600. Min Act: -0.0001

Data Index: 200752 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1530. Min Act: -0.0001

Data Index: 12970 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.2357. Min Range: -0.2357

Max Act: 0.1463. Min Act: -0.0000

Data Index: 582800 (C4 (Web Text))

Max Activating Token Index: 386