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

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

Neuron 2445 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: 1.6232. Min Range: -1.6232

Max Act: 1.6232. Min Act: -0.0001

Data Index: 1043635 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.3964. Min Act: -0.0001

Data Index: 448197 (C4 (Web Text))

Max Activating Token Index: 710

Text #2

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.2471. Min Act: -0.0001

Data Index: 1082591 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.1646. Min Act: -0.0001

Data Index: 1344850 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.2253. Min Act: -0.0001

Data Index: 1255269 (C4 (Web Text))

Max Activating Token Index: 488

Text #5

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.1348. Min Act: -0.0001

Data Index: 1354420 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.1462. Min Act: -0.0001

Data Index: 212809 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9944. Min Act: -0.0001

Data Index: 76387 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0391. Min Act: -0.0001

Data Index: 340788 (C4 (Web Text))

Max Activating Token Index: 837

Text #9

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9885. Min Act: -0.0001

Data Index: 95858 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9125. Min Act: -0.0001

Data Index: 1267088 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9794. Min Act: -0.0001

Data Index: 1212900 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0048. Min Act: -0.0001

Data Index: 1236463 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0246. Min Act: -0.0001

Data Index: 1105588 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9560. Min Act: -0.0001

Data Index: 1318881 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.8745. Min Act: -0.0001

Data Index: 1052188 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9262. Min Act: -0.0001

Data Index: 312831 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9513. Min Act: -0.0001

Data Index: 815056 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 1.6232. Min Range: -1.6232

Max Act: 1.0053. Min Act: -0.0001

Data Index: 540862 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 1.6232. Min Range: -1.6232

Max Act: 0.9122. Min Act: -0.0001

Data Index: 632204 (C4 (Web Text))

Max Activating Token Index: 672