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

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

Neuron 1394 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: 2.3624. Min Range: -2.3624

Max Act: 2.3624. Min Act: -0.0000

Data Index: 1441574 (Python Code)

Max Activating Token Index: 1017

Text #1

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.8050. Min Act: -0.0000

Data Index: 1444709 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.7854. Min Act: -0.0000

Data Index: 1522870 (Python Code)

Max Activating Token Index: 55

Text #3

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1436975 (Python Code)

Max Activating Token Index: 666

Text #4

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.7191. Min Act: -0.0000

Data Index: 1640535 (Python Code)

Max Activating Token Index: 254

Text #5

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.6026. Min Act: -0.0000

Data Index: 1574655 (Python Code)

Max Activating Token Index: 240

Text #6

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1602769 (Python Code)

Max Activating Token Index: 298

Text #7

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.6008. Min Act: -0.0000

Data Index: 1624104 (Python Code)

Max Activating Token Index: 31

Text #8

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.6007. Min Act: -0.0000

Data Index: 1614218 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.5695. Min Act: -0.0000

Data Index: 1523170 (Python Code)

Max Activating Token Index: 805

Text #10

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1455476 (Python Code)

Max Activating Token Index: 204

Text #11

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.4376. Min Act: -0.0000

Data Index: 1459977 (Python Code)

Max Activating Token Index: 141

Text #12

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.6109. Min Act: -0.0000

Data Index: 1587298 (Python Code)

Max Activating Token Index: 581

Text #13

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.5671. Min Act: -0.0000

Data Index: 1503344 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.4726. Min Act: -0.0000

Data Index: 1482928 (Python Code)

Max Activating Token Index: 950

Text #15

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1640643 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1617266 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1361424 (Python Code)

Max Activating Token Index: 469

Text #18

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.4510. Min Act: -0.0000

Data Index: 1446417 (Python Code)

Max Activating Token Index: 573

Text #19

Max Range: 2.3624. Min Range: -2.3624

Max Act: 1.3539. Min Act: -0.0000

Data Index: 1425864 (Python Code)

Max Activating Token Index: 732