Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1207 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1263069 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.5137. Min Act: -0.0000

Data Index: 306518 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4302. Min Act: -0.0000

Data Index: 484999 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4078. Min Act: -0.0000

Data Index: 1483397 (Python Code)

Max Activating Token Index: 732

Text #4

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1606031 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1523919 (Python Code)

Max Activating Token Index: 923

Text #6

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1603141 (Python Code)

Max Activating Token Index: 1022

Text #7

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1360563 (Python Code)

Max Activating Token Index: 986

Text #8

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3883. Min Act: -0.0000

Data Index: 1236265 (C4 (Web Text))

Max Activating Token Index: 770

Text #9

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4157. Min Act: -0.0000

Data Index: 26587 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3930. Min Act: -0.0000

Data Index: 1410725 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1650326 (Python Code)

Max Activating Token Index: 852

Text #12

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4020. Min Act: -0.0000

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1398561 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1535672 (Python Code)

Max Activating Token Index: 903

Text #15

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1443752 (Python Code)

Max Activating Token Index: 851

Text #16

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1398254 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1614639 (Python Code)

Max Activating Token Index: 770

Text #18

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1363113 (Python Code)

Max Activating Token Index: 838

Text #19

Max Range: 0.5137. Min Range: -0.5137

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1502454 (Python Code)

Max Activating Token Index: 888