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

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

Neuron 5206 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1665. Min Act: -0.0000

Data Index: 662930 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1482. Min Act: -0.0000

Data Index: 370715 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1445. Min Act: -0.0000

Data Index: 885941 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1497. Min Act: -0.0000

Data Index: 955026 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1396. Min Act: -0.0000

Data Index: 1004565 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1335. Min Act: -0.0000

Data Index: 463678 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1151. Min Act: -0.0000

Data Index: 619945 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1125. Min Act: -0.0000

Data Index: 481828 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1103. Min Act: -0.0000

Data Index: 441612 (C4 (Web Text))

Max Activating Token Index: 104

Text #9

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1127445 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1087. Min Act: -0.0000

Data Index: 940105 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1117. Min Act: -0.0000

Data Index: 695863 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1057. Min Act: -0.0000

Data Index: 409822 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1026. Min Act: -0.0000

Data Index: 476603 (C4 (Web Text))

Max Activating Token Index: 58

Text #14

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.0994. Min Act: -0.0000

Data Index: 43462 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.0970. Min Act: -0.0000

Data Index: 824724 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1002. Min Act: -0.0000

Data Index: 1077551 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1004. Min Act: -0.0000

Data Index: 383330 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1338414 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1009. Min Act: -0.0000

Data Index: 100602 (C4 (Web Text))

Max Activating Token Index: 642