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

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

Neuron 4767 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0402. Min Range: -2.0402

Max Act: 2.0165. Min Act: -0.0000

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 2.0402. Min Range: -2.0402

Max Act: 2.0402. Min Act: -0.0000

Data Index: 223525 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 2.0402. Min Range: -2.0402

Max Act: 1.1487. Min Act: -0.0000

Data Index: 1267237 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 2.0402. Min Range: -2.0402

Max Act: 1.1287. Min Act: -0.0000

Data Index: 408801 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 2.0402. Min Range: -2.0402

Max Act: 1.0670. Min Act: -0.0000

Data Index: 99580 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.9309. Min Act: -0.0000

Data Index: 62813 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.9563. Min Act: -0.0000

Data Index: 507589 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1147416 (C4 (Web Text))

Max Activating Token Index: 967

Text #8

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1210234 (C4 (Web Text))

Max Activating Token Index: 446

Text #9

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.9786. Min Act: -0.0000

Data Index: 564389 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.9020. Min Act: -0.0000

Data Index: 170140 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8458. Min Act: -0.0000

Data Index: 763907 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8728. Min Act: -0.0000

Data Index: 651454 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8478. Min Act: -0.0000

Data Index: 1042556 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8445. Min Act: -0.0000

Data Index: 165809 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8229. Min Act: 0.0000

Data Index: 977194 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8254. Min Act: -0.0000

Data Index: 1189388 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.7920. Min Act: -0.0000

Data Index: 1068401 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.7957. Min Act: -0.0000

Data Index: 1068770 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 2.0402. Min Range: -2.0402

Max Act: 0.8351. Min Act: 0.0000

Data Index: 826931 (C4 (Web Text))

Max Activating Token Index: 849