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

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

Neuron 4106 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.4422. Min Act: -0.0001

Data Index: 1460418 (Python Code)

Max Activating Token Index: 873

Text #1

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3858. Min Act: -0.0000

Data Index: 1568278 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3655. Min Act: -0.0001

Data Index: 1559707 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3497. Min Act: -0.0000

Data Index: 1617346 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3398. Min Act: -0.0001

Data Index: 1518124 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2847. Min Act: -0.0000

Data Index: 1632692 (Python Code)

Max Activating Token Index: 232

Text #6

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3613. Min Act: -0.0001

Data Index: 1568521 (Python Code)

Max Activating Token Index: 500

Text #7

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3564. Min Act: -0.0001

Data Index: 1573910 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3316. Min Act: -0.0001

Data Index: 1514726 (Python Code)

Max Activating Token Index: 8

Text #9

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3498. Min Act: -0.0001

Data Index: 1632273 (Python Code)

Max Activating Token Index: 333

Text #10

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1426575 (Python Code)

Max Activating Token Index: 221

Text #11

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1571135 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.2883. Min Act: -0.0000

Data Index: 1420857 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1590208 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1437233 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3171. Min Act: -0.0000

Data Index: 1635959 (Python Code)

Max Activating Token Index: 834

Text #16

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1454139 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3276. Min Act: -0.0000

Data Index: 1553964 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1491588 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 0.4422. Min Range: -0.4422

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1471169 (Python Code)

Max Activating Token Index: 6