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

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

Neuron 2833 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5477. Min Range: -5.5477

Max Act: 5.5477. Min Act: -0.0001

Data Index: 172850 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 5.5477. Min Range: -5.5477

Max Act: 5.3195. Min Act: -0.0001

Data Index: 628086 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 5.5477. Min Range: -5.5477

Max Act: 4.0360. Min Act: -0.0001

Data Index: 899683 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.5064. Min Act: -0.0001

Data Index: 475735 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.5492. Min Act: -0.0001

Data Index: 73915 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.3336. Min Act: -0.0000

Data Index: 780662 (C4 (Web Text))

Max Activating Token Index: 174

Text #6

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.4505. Min Act: -0.0001

Data Index: 886169 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.5968. Min Act: -0.0001

Data Index: 1304987 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.6376. Min Act: -0.0001

Data Index: 1263049 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.0125. Min Act: -0.0001

Data Index: 327697 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.5806. Min Act: -0.0000

Data Index: 401194 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 5.5477. Min Range: -5.5477

Max Act: 2.9393. Min Act: -0.0001

Data Index: 618914 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 5.5477. Min Range: -5.5477

Max Act: 2.9398. Min Act: -0.0000

Data Index: 1343045 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 5.5477. Min Range: -5.5477

Max Act: 2.6885. Min Act: -0.0000

Data Index: 560485 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 5.5477. Min Range: -5.5477

Max Act: 2.9348. Min Act: -0.0001

Data Index: 595044 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.0348. Min Act: -0.0001

Data Index: 1309833 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 5.5477. Min Range: -5.5477

Max Act: 2.8959. Min Act: -0.0001

Data Index: 317912 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.0071. Min Act: -0.0000

Data Index: 935166 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.2961. Min Act: -0.0000

Data Index: 127629 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 5.5477. Min Range: -5.5477

Max Act: 3.2461. Min Act: -0.0001

Data Index: 1034878 (C4 (Web Text))

Max Activating Token Index: 721