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

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

Neuron 1531 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4563. Min Act: -0.0001

Data Index: 1479659 (Python Code)

Max Activating Token Index: 1011

Text #1

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3246. Min Act: -0.0001

Data Index: 1373602 (Python Code)

Max Activating Token Index: 811

Text #2

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3730. Min Act: -0.0001

Data Index: 1600902 (Python Code)

Max Activating Token Index: 839

Text #3

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4787. Min Act: -0.0001

Data Index: 1445057 (Python Code)

Max Activating Token Index: 992

Text #4

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1381681 (Python Code)

Max Activating Token Index: 1014

Text #5

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3870. Min Act: -0.0001

Data Index: 1417480 (Python Code)

Max Activating Token Index: 700

Text #6

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3695. Min Act: -0.0001

Data Index: 1588426 (Python Code)

Max Activating Token Index: 191

Text #7

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3943. Min Act: -0.0001

Data Index: 1528979 (Python Code)

Max Activating Token Index: 831

Text #8

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4305. Min Act: -0.0001

Data Index: 1483261 (Python Code)

Max Activating Token Index: 1007

Text #9

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3792. Min Act: -0.0001

Data Index: 1510981 (Python Code)

Max Activating Token Index: 802

Text #10

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4664. Min Act: -0.0001

Data Index: 1553677 (Python Code)

Max Activating Token Index: 248

Text #11

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4328. Min Act: -0.0001

Data Index: 1655722 (Python Code)

Max Activating Token Index: 1014

Text #12

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.4157. Min Act: -0.0001

Data Index: 1611273 (Python Code)

Max Activating Token Index: 1007

Text #13

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3699. Min Act: -0.0001

Data Index: 1548536 (Python Code)

Max Activating Token Index: 996

Text #14

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3670. Min Act: -0.0001

Data Index: 1520552 (Python Code)

Max Activating Token Index: 510

Text #15

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3264. Min Act: -0.0001

Data Index: 1529716 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.2661. Min Act: -0.0001

Data Index: 1422197 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3524. Min Act: -0.0001

Data Index: 1400546 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.2878. Min Act: -0.0001

Data Index: 1373874 (Python Code)

Max Activating Token Index: 768

Text #19

Max Range: 0.4787. Min Range: -0.4787

Max Act: 0.3011. Min Act: -0.0001

Data Index: 1560527 (Python Code)

Max Activating Token Index: 273