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

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

Neuron 2541 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.4275. Min Act: -0.0001

Data Index: 962043 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.4504. Min Act: -0.0000

Data Index: 539387 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3838. Min Act: -0.0000

Data Index: 377673 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3541. Min Act: -0.0001

Data Index: 1551906 (Python Code)

Max Activating Token Index: 844

Text #4

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3465. Min Act: -0.0001

Data Index: 1442495 (Python Code)

Max Activating Token Index: 389

Text #5

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3463. Min Act: -0.0000

Data Index: 873410 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1254920 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3149. Min Act: -0.0001

Data Index: 571530 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3214. Min Act: -0.0000

Data Index: 1154868 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3225. Min Act: -0.0001

Data Index: 505399 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3112. Min Act: -0.0000

Data Index: 381154 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3212. Min Act: -0.0001

Data Index: 683684 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3128. Min Act: -0.0000

Data Index: 441898 (C4 (Web Text))

Max Activating Token Index: 214

Text #13

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3011. Min Act: -0.0001

Data Index: 578836 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1311722 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1149895 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2994. Min Act: -0.0001

Data Index: 1639895 (Python Code)

Max Activating Token Index: 168

Text #17

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1200254 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.3046. Min Act: -0.0000

Data Index: 1060150 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.4504. Min Range: -0.4504

Max Act: 0.2920. Min Act: -0.0000

Data Index: 207880 (C4 (Web Text))

Max Activating Token Index: 1020