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

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

Neuron 4970 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4423. Min Range: -3.4423

Max Act: 3.4423. Min Act: -0.0000

Data Index: 868769 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.5387. Min Act: -0.0000

Data Index: 1238287 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.4583. Min Act: -0.0000

Data Index: 1331345 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.4017. Min Act: -0.0000

Data Index: 432326 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.1412. Min Act: -0.0000

Data Index: 1064412 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.1144. Min Act: -0.0000

Data Index: 1229666 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.1014. Min Act: -0.0000

Data Index: 578888 (C4 (Web Text))

Max Activating Token Index: 1014

Text #7

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.0266. Min Act: -0.0000

Data Index: 458538 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.0000. Min Act: -0.0000

Data Index: 963431 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.0676. Min Act: -0.0000

Data Index: 686220 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.8897. Min Act: -0.0000

Data Index: 351352 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.8313. Min Act: -0.0000

Data Index: 74750 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.7833. Min Act: -0.0000

Data Index: 663693 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.0294. Min Act: -0.0000

Data Index: 634534 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 3.4423. Min Range: -3.4423

Max Act: 2.0042. Min Act: -0.0000

Data Index: 220796 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.8623. Min Act: -0.0000

Data Index: 319646 (C4 (Web Text))

Max Activating Token Index: 82

Text #16

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.8430. Min Act: -0.0000

Data Index: 1173384 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.8361. Min Act: -0.0000

Data Index: 613531 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.8896. Min Act: -0.0000

Data Index: 807106 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 3.4423. Min Range: -3.4423

Max Act: 1.8259. Min Act: -0.0000

Data Index: 1215944 (C4 (Web Text))

Max Activating Token Index: 557