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

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

Neuron 1950 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7569. Min Act: -0.0002

Data Index: 1371796 (Python Code)

Max Activating Token Index: 706

Text #1

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7265. Min Act: -0.0002

Data Index: 1627296 (Python Code)

Max Activating Token Index: 659

Text #2

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6729. Min Act: -0.0002

Data Index: 1475275 (Python Code)

Max Activating Token Index: 533

Text #3

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7139. Min Act: -0.0002

Data Index: 1609402 (Python Code)

Max Activating Token Index: 181

Text #4

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6723. Min Act: -0.0002

Data Index: 1408665 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6700. Min Act: -0.0002

Data Index: 1605451 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6651. Min Act: -0.0002

Data Index: 1415126 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6628. Min Act: -0.0002

Data Index: 1582888 (Python Code)

Max Activating Token Index: 43

Text #8

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6505. Min Act: -0.0002

Data Index: 1566736 (Python Code)

Max Activating Token Index: 223

Text #9

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6484. Min Act: -0.0002

Data Index: 1555612 (Python Code)

Max Activating Token Index: 469

Text #10

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6450. Min Act: -0.0002

Data Index: 1411343 (Python Code)

Max Activating Token Index: 649

Text #11

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6448. Min Act: -0.0002

Data Index: 1602905 (Python Code)

Max Activating Token Index: 678

Text #12

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6420. Min Act: -0.0002

Data Index: 1610830 (Python Code)

Max Activating Token Index: 106

Text #13

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6410. Min Act: -0.0002

Data Index: 1405389 (Python Code)

Max Activating Token Index: 799

Text #14

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6401. Min Act: -0.0002

Data Index: 1473726 (Python Code)

Max Activating Token Index: 856

Text #15

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6597. Min Act: -0.0002

Data Index: 1522418 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6375. Min Act: -0.0002

Data Index: 1369632 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6369. Min Act: -0.0002

Data Index: 1479231 (Python Code)

Max Activating Token Index: 32

Text #18

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6363. Min Act: -0.0002

Data Index: 1425833 (Python Code)

Max Activating Token Index: 382

Text #19

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6335. Min Act: -0.0002

Data Index: 1595861 (Python Code)

Max Activating Token Index: 612