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

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

Neuron 2763 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1580703 (Python Code)

Max Activating Token Index: 594

Text #1

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1499310 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1507108 (Python Code)

Max Activating Token Index: 823

Text #3

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1261. Min Act: -0.0001

Data Index: 1551515 (Python Code)

Max Activating Token Index: 1010

Text #4

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1284. Min Act: -0.0001

Data Index: 1655649 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1481340 (Python Code)

Max Activating Token Index: 622

Text #6

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1515024 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1646748 (Python Code)

Max Activating Token Index: 467

Text #8

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1595104 (Python Code)

Max Activating Token Index: 464

Text #9

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1477530 (Python Code)

Max Activating Token Index: 736

Text #10

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1131. Min Act: -0.0001

Data Index: 1511999 (Python Code)

Max Activating Token Index: 566

Text #11

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1369122 (Python Code)

Max Activating Token Index: 558

Text #12

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1154. Min Act: -0.0001

Data Index: 1372540 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1141. Min Act: -0.0000

Data Index: 1534804 (Python Code)

Max Activating Token Index: 44

Text #14

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1183. Min Act: -0.0001

Data Index: 1476230 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1441584 (Python Code)

Max Activating Token Index: 433

Text #16

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1132. Min Act: -0.0001

Data Index: 1443605 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1402433 (Python Code)

Max Activating Token Index: 478

Text #18

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1364860 (Python Code)

Max Activating Token Index: 302

Text #19

Max Range: 0.1481. Min Range: -0.1481

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1524112 (Python Code)

Max Activating Token Index: 863