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

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

Neuron 736 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: 0.1681. Min Range: -0.1681

Max Act: 0.1681. Min Act: -0.0003

Data Index: 1430767 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1677. Min Act: -0.0003

Data Index: 1614420 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1575. Min Act: -0.0003

Data Index: 1540349 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1535. Min Act: -0.0003

Data Index: 1442210 (Python Code)

Max Activating Token Index: 386

Text #4

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1564. Min Act: -0.0003

Data Index: 1611149 (Python Code)

Max Activating Token Index: 292

Text #5

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1549. Min Act: -0.0003

Data Index: 1410972 (Python Code)

Max Activating Token Index: 63

Text #6

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1550. Min Act: -0.0003

Data Index: 1363127 (Python Code)

Max Activating Token Index: 523

Text #7

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1546. Min Act: -0.0003

Data Index: 1379723 (Python Code)

Max Activating Token Index: 386

Text #8

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1521. Min Act: -0.0003

Data Index: 1588029 (Python Code)

Max Activating Token Index: 479

Text #9

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1505. Min Act: -0.0003

Data Index: 1547840 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1522. Min Act: -0.0003

Data Index: 1396452 (Python Code)

Max Activating Token Index: 128

Text #11

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1502. Min Act: -0.0003

Data Index: 1430470 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1501. Min Act: -0.0003

Data Index: 1646162 (Python Code)

Max Activating Token Index: 46

Text #13

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1479. Min Act: -0.0003

Data Index: 1477835 (Python Code)

Max Activating Token Index: 712

Text #14

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1523. Min Act: -0.0003

Data Index: 1612906 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1464. Min Act: -0.0003

Data Index: 1399878 (Python Code)

Max Activating Token Index: 352

Text #16

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1487. Min Act: -0.0003

Data Index: 1546801 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1492. Min Act: -0.0003

Data Index: 1383100 (Python Code)

Max Activating Token Index: 240

Text #18

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1502. Min Act: -0.0003

Data Index: 1394990 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.1681. Min Range: -0.1681

Max Act: 0.1459. Min Act: -0.0003

Data Index: 1626022 (Python Code)

Max Activating Token Index: 416