Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 826 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1479. Min Act: -0.0003

Data Index: 1479482 (Python Code)

Max Activating Token Index: 274

Text #1

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1257. Min Act: -0.0003

Data Index: 1466783 (Python Code)

Max Activating Token Index: 326

Text #2

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1305. Min Act: -0.0003

Data Index: 1406886 (Python Code)

Max Activating Token Index: 513

Text #3

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1263. Min Act: -0.0003

Data Index: 1625412 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1212. Min Act: -0.0003

Data Index: 1496004 (Python Code)

Max Activating Token Index: 182

Text #5

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1230. Min Act: -0.0003

Data Index: 1395657 (Python Code)

Max Activating Token Index: 510

Text #6

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1202. Min Act: -0.0003

Data Index: 1524744 (Python Code)

Max Activating Token Index: 545

Text #7

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1120. Min Act: -0.0003

Data Index: 1596966 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1137. Min Act: -0.0003

Data Index: 1654561 (Python Code)

Max Activating Token Index: 611

Text #9

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1115. Min Act: -0.0003

Data Index: 1606456 (Python Code)

Max Activating Token Index: 346

Text #10

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1111. Min Act: -0.0003

Data Index: 1364528 (Python Code)

Max Activating Token Index: 147

Text #11

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1145. Min Act: -0.0003

Data Index: 1594101 (Python Code)

Max Activating Token Index: 454

Text #12

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1453599 (Python Code)

Max Activating Token Index: 478

Text #13

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1127. Min Act: -0.0003

Data Index: 1420834 (Python Code)

Max Activating Token Index: 198

Text #14

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1168. Min Act: -0.0003

Data Index: 1624329 (Python Code)

Max Activating Token Index: 686

Text #15

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1164. Min Act: -0.0003

Data Index: 1499898 (Python Code)

Max Activating Token Index: 230

Text #16

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1080. Min Act: -0.0003

Data Index: 1399430 (Python Code)

Max Activating Token Index: 403

Text #17

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1107. Min Act: -0.0003

Data Index: 1427455 (Python Code)

Max Activating Token Index: 587

Text #18

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1103. Min Act: -0.0003

Data Index: 1459379 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 0.1479. Min Range: -0.1479

Max Act: 0.1085. Min Act: -0.0003

Data Index: 1622134 (Python Code)

Max Activating Token Index: 155