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

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

Neuron 1413 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1143213 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1093. Min Act: -0.0000

Data Index: 643381 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1356. Min Act: -0.0000

Data Index: 315140 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1351. Min Act: -0.0000

Data Index: 416167 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1351. Min Act: -0.0000

Data Index: 501575 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1335. Min Act: 0.0000

Data Index: 1314624 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1316. Min Act: -0.0000

Data Index: 9665 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1244. Min Act: -0.0000

Data Index: 200343 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1277. Min Act: -0.0000

Data Index: 4266 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1305. Min Act: -0.0000

Data Index: 751363 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1192. Min Act: -0.0000

Data Index: 366299 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1223. Min Act: -0.0000

Data Index: 1421018 (Python Code)

Max Activating Token Index: 65

Text #12

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1516469 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1192. Min Act: -0.0000

Data Index: 69045 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1283. Min Act: -0.0000

Data Index: 364549 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1231674 (C4 (Web Text))

Max Activating Token Index: 49

Text #16

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1153. Min Act: -0.0000

Data Index: 1115399 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1274. Min Act: -0.0000

Data Index: 1000560 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1159. Min Act: -0.0000

Data Index: 173892 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.1757. Min Range: -0.1757

Max Act: 0.1177. Min Act: -0.0000

Data Index: 733061 (C4 (Web Text))

Max Activating Token Index: 560