Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4621. Min Act: -0.0001

Data Index: 1419077 (Python Code)

Max Activating Token Index: 208

Text #1

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4463. Min Act: -0.0001

Data Index: 1613454 (Python Code)

Max Activating Token Index: 113

Text #2

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4079. Min Act: -0.0001

Data Index: 1486989 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4069. Min Act: -0.0001

Data Index: 1380741 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1533925 (Python Code)

Max Activating Token Index: 445

Text #5

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.4040. Min Act: -0.0001

Data Index: 1493492 (Python Code)

Max Activating Token Index: 885

Text #6

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1607349 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3820. Min Act: -0.0001

Data Index: 1428059 (Python Code)

Max Activating Token Index: 50

Text #8

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3894. Min Act: -0.0001

Data Index: 1379564 (Python Code)

Max Activating Token Index: 693

Text #9

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1420320 (Python Code)

Max Activating Token Index: 950

Text #10

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3642. Min Act: -0.0001

Data Index: 1565952 (Python Code)

Max Activating Token Index: 111

Text #11

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3474. Min Act: -0.0001

Data Index: 1570936 (Python Code)

Max Activating Token Index: 920

Text #12

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1613917 (Python Code)

Max Activating Token Index: 959

Text #13

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3969. Min Act: -0.0001

Data Index: 1378122 (Python Code)

Max Activating Token Index: 601

Text #14

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3556. Min Act: -0.0001

Data Index: 1385045 (Python Code)

Max Activating Token Index: 883

Text #15

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3532. Min Act: -0.0001

Data Index: 1618755 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3656. Min Act: -0.0001

Data Index: 1593760 (Python Code)

Max Activating Token Index: 742

Text #17

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3630. Min Act: -0.0001

Data Index: 1468669 (Python Code)

Max Activating Token Index: 72

Text #18

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3712. Min Act: -0.0001

Data Index: 1531578 (Python Code)

Max Activating Token Index: 688

Text #19

Max Range: 0.4621. Min Range: -0.4621

Max Act: 0.3585. Min Act: -0.0001

Data Index: 1444399 (Python Code)

Max Activating Token Index: 20