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

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

Neuron 4992 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: 0.1538. Min Range: -0.1538

Max Act: 0.1538. Min Act: -0.0000

Data Index: 754075 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1393. Min Act: -0.0000

Data Index: 871344 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1187943 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1345. Min Act: -0.0000

Data Index: 492253 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1381. Min Act: -0.0000

Data Index: 801924 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1381. Min Act: -0.0000

Data Index: 1337442 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1330. Min Act: -0.0000

Data Index: 327016 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1397. Min Act: -0.0000

Data Index: 886387 (C4 (Web Text))

Max Activating Token Index: 793

Text #8

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1301. Min Act: -0.0000

Data Index: 175215 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1369. Min Act: -0.0000

Data Index: 616042 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1260. Min Act: -0.0000

Data Index: 55344 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1286. Min Act: -0.0000

Data Index: 811772 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1280. Min Act: -0.0000

Data Index: 911926 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1360. Min Act: -0.0000

Data Index: 704724 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1271. Min Act: -0.0000

Data Index: 584301 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1302481 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1165. Min Act: -0.0000

Data Index: 419588 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1215. Min Act: -0.0000

Data Index: 777351 (C4 (Web Text))

Max Activating Token Index: 864

Text #18

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1174. Min Act: -0.0000

Data Index: 647130 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.1538. Min Range: -0.1538

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1191658 (C4 (Web Text))

Max Activating Token Index: 356