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

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

Neuron 2824 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: 4.1042. Min Range: -4.1042

Max Act: 4.1042. Min Act: -0.0000

Data Index: 1412136 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 4.1042. Min Range: -4.1042

Max Act: 3.5456. Min Act: -0.0000

Data Index: 1635234 (Python Code)

Max Activating Token Index: 934

Text #2

Max Range: 4.1042. Min Range: -4.1042

Max Act: 3.5443. Min Act: -0.0000

Data Index: 1531609 (Python Code)

Max Activating Token Index: 955

Text #3

Max Range: 4.1042. Min Range: -4.1042

Max Act: 3.4389. Min Act: -0.0000

Data Index: 1493429 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 4.1042. Min Range: -4.1042

Max Act: 3.3636. Min Act: -0.0000

Data Index: 1649622 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 4.1042. Min Range: -4.1042

Max Act: 3.2433. Min Act: -0.0000

Data Index: 1444746 (Python Code)

Max Activating Token Index: 370

Text #6

Max Range: 4.1042. Min Range: -4.1042

Max Act: 3.3487. Min Act: -0.0000

Data Index: 1400759 (Python Code)

Max Activating Token Index: 423

Text #7

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.8994. Min Act: -0.0000

Data Index: 1633034 (Python Code)

Max Activating Token Index: 865

Text #8

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.9652. Min Act: -0.0000

Data Index: 1615447 (Python Code)

Max Activating Token Index: 831

Text #9

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.9644. Min Act: -0.0000

Data Index: 1572535 (Python Code)

Max Activating Token Index: 898

Text #10

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.8382. Min Act: -0.0000

Data Index: 1399231 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.9593. Min Act: -0.0000

Data Index: 1536960 (Python Code)

Max Activating Token Index: 854

Text #12

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.8148. Min Act: -0.0000

Data Index: 1598789 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.7726. Min Act: -0.0000

Data Index: 1424042 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.8854. Min Act: -0.0000

Data Index: 1634665 (Python Code)

Max Activating Token Index: 818

Text #15

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.7039. Min Act: -0.0000

Data Index: 1505355 (Python Code)

Max Activating Token Index: 545

Text #16

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.7867. Min Act: -0.0000

Data Index: 1426784 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.6354. Min Act: -0.0000

Data Index: 1646942 (Python Code)

Max Activating Token Index: 902

Text #18

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.6296. Min Act: -0.0000

Data Index: 1548525 (Python Code)

Max Activating Token Index: 1016

Text #19

Max Range: 4.1042. Min Range: -4.1042

Max Act: 2.6016. Min Act: -0.0000

Data Index: 1637635 (Python Code)

Max Activating Token Index: 736