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

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

Neuron 4905 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7616. Min Range: -4.7616

Max Act: 4.7616. Min Act: -0.0000

Data Index: 1565505 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 4.7616. Min Range: -4.7616

Max Act: 4.3680. Min Act: -0.0000

Data Index: 1521227 (Python Code)

Max Activating Token Index: 542

Text #2

Max Range: 4.7616. Min Range: -4.7616

Max Act: 4.4852. Min Act: -0.0000

Data Index: 1523171 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 4.7616. Min Range: -4.7616

Max Act: 3.9992. Min Act: -0.0000

Data Index: 1367701 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 4.7616. Min Range: -4.7616

Max Act: 3.8521. Min Act: -0.0000

Data Index: 1507849 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 4.7616. Min Range: -4.7616

Max Act: 3.8006. Min Act: -0.0000

Data Index: 1405912 (Python Code)

Max Activating Token Index: 779

Text #6

Max Range: 4.7616. Min Range: -4.7616

Max Act: 3.4979. Min Act: -0.0000

Data Index: 1390611 (Python Code)

Max Activating Token Index: 170

Text #7

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6637. Min Act: -0.0000

Data Index: 1396006 (Python Code)

Max Activating Token Index: 716

Text #8

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.8031. Min Act: -0.0000

Data Index: 1462063 (Python Code)

Max Activating Token Index: 22

Text #9

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6530. Min Act: -0.0000

Data Index: 1583220 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6066. Min Act: -0.0000

Data Index: 1425662 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.7213. Min Act: -0.0000

Data Index: 1407412 (Python Code)

Max Activating Token Index: 814

Text #12

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6554. Min Act: -0.0000

Data Index: 1504730 (Python Code)

Max Activating Token Index: 650

Text #13

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6310. Min Act: -0.0000

Data Index: 1407758 (Python Code)

Max Activating Token Index: 475

Text #14

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.5035. Min Act: -0.0000

Data Index: 1619230 (Python Code)

Max Activating Token Index: 661

Text #15

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6261. Min Act: -0.0000

Data Index: 1367858 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.4186. Min Act: -0.0000

Data Index: 1594575 (Python Code)

Max Activating Token Index: 414

Text #17

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6387. Min Act: -0.0000

Data Index: 1394947 (Python Code)

Max Activating Token Index: 885

Text #18

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.6547. Min Act: 0.0000

Data Index: 1572640 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 4.7616. Min Range: -4.7616

Max Act: 2.5154. Min Act: -0.0000

Data Index: 1581314 (Python Code)

Max Activating Token Index: 843