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

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

Neuron 1624 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: 3.6323. Min Range: -3.6323

Max Act: 3.6323. Min Act: -0.0001

Data Index: 1424772 (Python Code)

Max Activating Token Index: 165

Text #1

Max Range: 3.6323. Min Range: -3.6323

Max Act: 3.2818. Min Act: -0.0000

Data Index: 1549852 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 3.6323. Min Range: -3.6323

Max Act: 3.4203. Min Act: -0.0001

Data Index: 1625360 (Python Code)

Max Activating Token Index: 448

Text #3

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.9656. Min Act: -0.0000

Data Index: 1644726 (Python Code)

Max Activating Token Index: 809

Text #4

Max Range: 3.6323. Min Range: -3.6323

Max Act: 3.2210. Min Act: -0.0000

Data Index: 1586307 (Python Code)

Max Activating Token Index: 717

Text #5

Max Range: 3.6323. Min Range: -3.6323

Max Act: 3.0184. Min Act: -0.0000

Data Index: 1461763 (Python Code)

Max Activating Token Index: 212

Text #6

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.9637. Min Act: -0.0000

Data Index: 1646827 (Python Code)

Max Activating Token Index: 228

Text #7

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.9607. Min Act: -0.0001

Data Index: 1499976 (Python Code)

Max Activating Token Index: 784

Text #8

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.9496. Min Act: -0.0000

Data Index: 1477188 (Python Code)

Max Activating Token Index: 372

Text #9

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.7935. Min Act: -0.0001

Data Index: 1518705 (Python Code)

Max Activating Token Index: 136

Text #10

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.8640. Min Act: 0.0000

Data Index: 1416678 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.9783. Min Act: -0.0001

Data Index: 1501560 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.8284. Min Act: -0.0001

Data Index: 1494468 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.8008. Min Act: -0.0001

Data Index: 1481216 (Python Code)

Max Activating Token Index: 289

Text #14

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.7786. Min Act: -0.0001

Data Index: 1628688 (Python Code)

Max Activating Token Index: 714

Text #15

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.7668. Min Act: -0.0000

Data Index: 1499791 (Python Code)

Max Activating Token Index: 200

Text #16

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.7362. Min Act: -0.0001

Data Index: 1640196 (Python Code)

Max Activating Token Index: 861

Text #17

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.5922. Min Act: -0.0001

Data Index: 1476559 (Python Code)

Max Activating Token Index: 371

Text #18

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.5132. Min Act: -0.0000

Data Index: 1530429 (Python Code)

Max Activating Token Index: 531

Text #19

Max Range: 3.6323. Min Range: -3.6323

Max Act: 2.5871. Min Act: -0.0001

Data Index: 1411691 (Python Code)

Max Activating Token Index: 696