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

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

Neuron 3831 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1437. Min Range: -2.1437

Max Act: 2.1302. Min Act: -0.0000

Data Index: 385941 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 2.1437. Min Range: -2.1437

Max Act: 2.1437. Min Act: -0.0000

Data Index: 387112 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.9095. Min Act: -0.0000

Data Index: 275672 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.8274. Min Act: -0.0000

Data Index: 1352282 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.8203. Min Act: -0.0000

Data Index: 1176860 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.7336. Min Act: -0.0000

Data Index: 792987 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.7180. Min Act: -0.0000

Data Index: 318928 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.5368. Min Act: -0.0000

Data Index: 844377 (C4 (Web Text))

Max Activating Token Index: 662

Text #8

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4766. Min Act: -0.0000

Data Index: 172269 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.5615. Min Act: -0.0000

Data Index: 720281 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4463. Min Act: -0.0000

Data Index: 796780 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4175. Min Act: -0.0000

Data Index: 738861 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4634. Min Act: -0.0000

Data Index: 509203 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4244. Min Act: -0.0000

Data Index: 453517 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.2628. Min Act: -0.0000

Data Index: 1019034 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4100. Min Act: -0.0000

Data Index: 411024 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.3305. Min Act: -0.0000

Data Index: 61767 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4844. Min Act: -0.0000

Data Index: 697103 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.4876. Min Act: -0.0000

Data Index: 1318409 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 2.1437. Min Range: -2.1437

Max Act: 1.2281. Min Act: -0.0000

Data Index: 910144 (C4 (Web Text))

Max Activating Token Index: 469