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

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

Neuron 1880 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: 0.1632. Min Range: -0.1632

Max Act: 0.1632. Min Act: -0.0001

Data Index: 233704 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1384. Min Act: -0.0001

Data Index: 130630 (C4 (Web Text))

Max Activating Token Index: 554

Text #2

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1402. Min Act: -0.0001

Data Index: 544714 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1064290 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1430. Min Act: -0.0001

Data Index: 519028 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1228447 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1308. Min Act: -0.0001

Data Index: 445433 (C4 (Web Text))

Max Activating Token Index: 838

Text #7

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1360. Min Act: -0.0001

Data Index: 126885 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1339. Min Act: -0.0001

Data Index: 959637 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1152410 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1267. Min Act: -0.0001

Data Index: 865926 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1309457 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1308118 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1239. Min Act: -0.0001

Data Index: 604009 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1316. Min Act: -0.0001

Data Index: 819446 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1097238 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1302. Min Act: -0.0001

Data Index: 287030 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1268. Min Act: -0.0001

Data Index: 1211843 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1355441 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 0.1632. Min Range: -0.1632

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1223491 (C4 (Web Text))

Max Activating Token Index: 554