Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3222 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7365. Min Act: -0.0001

Data Index: 17378 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7330. Min Act: -0.0001

Data Index: 514624 (C4 (Web Text))

Max Activating Token Index: 897

Text #2

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7120. Min Act: -0.0001

Data Index: 123628 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7088. Min Act: -0.0001

Data Index: 1339310 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6887. Min Act: -0.0001

Data Index: 642764 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7140. Min Act: -0.0001

Data Index: 1313080 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.7105. Min Act: -0.0001

Data Index: 850222 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6613. Min Act: -0.0001

Data Index: 635787 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6602. Min Act: -0.0001

Data Index: 1332301 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6846. Min Act: -0.0001

Data Index: 111204 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6800. Min Act: -0.0001

Data Index: 809059 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6383. Min Act: -0.0001

Data Index: 762621 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6549. Min Act: -0.0001

Data Index: 735541 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6536. Min Act: -0.0001

Data Index: 541590 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6988. Min Act: -0.0001

Data Index: 1285428 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6685. Min Act: -0.0001

Data Index: 572285 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6634. Min Act: -0.0001

Data Index: 1130094 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6301. Min Act: -0.0001

Data Index: 900480 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6784. Min Act: -0.0001

Data Index: 765981 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.7365. Min Range: -0.7365

Max Act: 0.6599. Min Act: -0.0001

Data Index: 605304 (C4 (Web Text))

Max Activating Token Index: 360