Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3180 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1305. Min Range: -1.1305

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1394026 (Python Code)

Max Activating Token Index: 658

Text #1

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1454349 (Python Code)

Max Activating Token Index: 956

Text #2

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.9723. Min Act: -0.0000

Data Index: 1445643 (Python Code)

Max Activating Token Index: 571

Text #3

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8944. Min Act: -0.0000

Data Index: 1594881 (Python Code)

Max Activating Token Index: 126

Text #4

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1393733 (Python Code)

Max Activating Token Index: 669

Text #5

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8897. Min Act: -0.0000

Data Index: 1648978 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1580871 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1528356 (Python Code)

Max Activating Token Index: 677

Text #8

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1482445 (Python Code)

Max Activating Token Index: 139

Text #9

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8841. Min Act: -0.0000

Data Index: 1567719 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1411352 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.6957. Min Act: -0.0000

Data Index: 1458166 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7671. Min Act: -0.0000

Data Index: 1503873 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1388162 (Python Code)

Max Activating Token Index: 58

Text #14

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7514. Min Act: -0.0000

Data Index: 1365139 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1602330 (Python Code)

Max Activating Token Index: 604

Text #16

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1386904 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7645. Min Act: -0.0000

Data Index: 1568046 (Python Code)

Max Activating Token Index: 806

Text #18

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1556621 (Python Code)

Max Activating Token Index: 474

Text #19

Max Range: 1.1305. Min Range: -1.1305

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1631703 (Python Code)

Max Activating Token Index: 928