Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2909 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1490. Min Act: -0.0001

Data Index: 54839 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1525. Min Act: -0.0001

Data Index: 376632 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1383. Min Act: -0.0001

Data Index: 892834 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1459. Min Act: -0.0001

Data Index: 944147 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1400. Min Act: -0.0001

Data Index: 1133853 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1326. Min Act: -0.0001

Data Index: 363567 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1410. Min Act: -0.0001

Data Index: 1518379 (Python Code)

Max Activating Token Index: 22

Text #7

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1383. Min Act: -0.0001

Data Index: 383999 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1191. Min Act: -0.0001

Data Index: 881848 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1245. Min Act: -0.0001

Data Index: 502151 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1287. Min Act: -0.0001

Data Index: 1062361 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1226. Min Act: -0.0001

Data Index: 686039 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1310. Min Act: -0.0001

Data Index: 45801 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1246. Min Act: -0.0001

Data Index: 638640 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1204. Min Act: -0.0001

Data Index: 457452 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1290. Min Act: -0.0001

Data Index: 576656 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1180. Min Act: -0.0001

Data Index: 256800 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1214. Min Act: -0.0001

Data Index: 132136 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1282. Min Act: -0.0001

Data Index: 755258 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 0.1525. Min Range: -0.1525

Max Act: 0.1333. Min Act: -0.0001

Data Index: 899022 (C4 (Web Text))

Max Activating Token Index: 836