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

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

Neuron 353 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0003

Data Index: 1593503 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1602468 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1559465 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1401135 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1606798 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1536263 (Python Code)

Max Activating Token Index: 632

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1615033 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0533. Min Act: -0.0003

Data Index: 1646109 (Python Code)

Max Activating Token Index: 15

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1633050 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1415496 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0552. Min Act: -0.0003

Data Index: 1482107 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1571361 (Python Code)

Max Activating Token Index: 380

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1407666 (Python Code)

Max Activating Token Index: 388

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1602937 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0464. Min Act: -0.0003

Data Index: 1447628 (Python Code)

Max Activating Token Index: 122

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1520141 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0455. Min Act: -0.0003

Data Index: 1361410 (Python Code)

Max Activating Token Index: 93

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0454. Min Act: -0.0003

Data Index: 1599871 (Python Code)

Max Activating Token Index: 40

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1597702 (Python Code)

Max Activating Token Index: 46

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1640520 (Python Code)

Max Activating Token Index: 34