Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5959 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.4681. Min Act: -0.0000

Data Index: 1549244 (Python Code)

Max Activating Token Index: 160

Text #1

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1362. Min Act: -0.0000

Data Index: 1588342 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1956. Min Act: -0.0000

Data Index: 1610184 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.1666. Min Act: -0.0000

Data Index: 1404956 (Python Code)

Max Activating Token Index: 691

Text #4

Max Range: 1.4681. Min Range: -1.4681

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1556534 (Python Code)

Max Activating Token Index: 24

Text #5

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1570862 (Python Code)

Max Activating Token Index: 949

Text #6

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9784. Min Act: -0.0000

Data Index: 1410733 (Python Code)

Max Activating Token Index: 27

Text #7

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1583973 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1637316 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1462842 (Python Code)

Max Activating Token Index: 627

Text #10

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9292. Min Act: -0.0000

Data Index: 1583595 (Python Code)

Max Activating Token Index: 201

Text #11

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9207. Min Act: -0.0000

Data Index: 1533503 (Python Code)

Max Activating Token Index: 417

Text #12

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1425424 (Python Code)

Max Activating Token Index: 558

Text #13

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1633194 (Python Code)

Max Activating Token Index: 218

Text #14

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.9185. Min Act: -0.0000

Data Index: 1378817 (Python Code)

Max Activating Token Index: 72

Text #15

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1541132 (Python Code)

Max Activating Token Index: 503

Text #16

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1364824 (Python Code)

Max Activating Token Index: 922

Text #17

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1571245 (Python Code)

Max Activating Token Index: 10

Text #18

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1533244 (Python Code)

Max Activating Token Index: 290

Text #19

Max Range: 1.4681. Min Range: -1.4681

Max Act: 0.8836. Min Act: -0.0000

Data Index: 851797 (C4 (Web Text))

Max Activating Token Index: 364