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

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

Neuron 2532 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1908. Min Act: -0.0003

Data Index: 565072 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1516. Min Act: -0.0003

Data Index: 893159 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1798. Min Act: -0.0003

Data Index: 588467 (C4 (Web Text))

Max Activating Token Index: 604

Text #3

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1539. Min Act: -0.0003

Data Index: 387238 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1495. Min Act: -0.0003

Data Index: 398519 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.0947. Min Act: -0.0003

Data Index: 613111 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1522. Min Act: -0.0003

Data Index: 639658 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1423. Min Act: -0.0003

Data Index: 1286595 (C4 (Web Text))

Max Activating Token Index: 538

Text #8

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1377. Min Act: -0.0003

Data Index: 818247 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1387. Min Act: -0.0003

Data Index: 1043726 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1339. Min Act: -0.0003

Data Index: 299677 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1626. Min Act: -0.0003

Data Index: 1052521 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1282. Min Act: -0.0003

Data Index: 54724 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1299. Min Act: -0.0003

Data Index: 670043 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1259. Min Act: -0.0003

Data Index: 890613 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1358. Min Act: -0.0003

Data Index: 169114 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1267. Min Act: -0.0003

Data Index: 1346936 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1217. Min Act: -0.0003

Data Index: 297420 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1204. Min Act: -0.0003

Data Index: 534528 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 0.1908. Min Range: -0.1908

Max Act: 0.1123. Min Act: -0.0003

Data Index: 352348 (C4 (Web Text))

Max Activating Token Index: 279