Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2997 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.2958. Min Act: -0.0001

Data Index: 1395372 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.1095. Min Act: -0.0001

Data Index: 1469471 (Python Code)

Max Activating Token Index: 464

Text #2

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.2357. Min Act: -0.0001

Data Index: 1363722 (Python Code)

Max Activating Token Index: 326

Text #3

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.2212. Min Act: -0.0001

Data Index: 1374659 (Python Code)

Max Activating Token Index: 167

Text #4

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.5075. Min Act: -0.0001

Data Index: 1452939 (Python Code)

Max Activating Token Index: 673

Text #5

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.3416. Min Act: -0.0001

Data Index: 1379171 (Python Code)

Max Activating Token Index: 473

Text #6

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.2344. Min Act: -0.0001

Data Index: 1413101 (Python Code)

Max Activating Token Index: 632

Text #7

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.2052. Min Act: -0.0001

Data Index: 1603059 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.0360. Min Act: -0.0001

Data Index: 1422954 (Python Code)

Max Activating Token Index: 442

Text #9

Max Range: 3.5075. Min Range: -3.5075

Max Act: 2.8737. Min Act: -0.0001

Data Index: 1466637 (Python Code)

Max Activating Token Index: 677

Text #10

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.0234. Min Act: -0.0001

Data Index: 1430006 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 3.5075. Min Range: -3.5075

Max Act: 2.9632. Min Act: -0.0001

Data Index: 1380040 (Python Code)

Max Activating Token Index: 383

Text #12

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.0873. Min Act: -0.0001

Data Index: 1481993 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 3.5075. Min Range: -3.5075

Max Act: 2.9411. Min Act: -0.0001

Data Index: 1387417 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.0779. Min Act: -0.0001

Data Index: 1414879 (Python Code)

Max Activating Token Index: 191

Text #15

Max Range: 3.5075. Min Range: -3.5075

Max Act: 3.0411. Min Act: -0.0001

Data Index: 1414946 (Python Code)

Max Activating Token Index: 331

Text #16

Max Range: 3.5075. Min Range: -3.5075

Max Act: 2.8848. Min Act: -0.0001

Data Index: 1416427 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 3.5075. Min Range: -3.5075

Max Act: 2.8793. Min Act: -0.0001

Data Index: 1588987 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 3.5075. Min Range: -3.5075

Max Act: 2.7382. Min Act: -0.0001

Data Index: 1483319 (Python Code)

Max Activating Token Index: 658

Text #19

Max Range: 3.5075. Min Range: -3.5075

Max Act: 2.8489. Min Act: -0.0001

Data Index: 1628942 (Python Code)

Max Activating Token Index: 73