Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 543 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1387029 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0006

Data Index: 1540571 (Python Code)

Max Activating Token Index: 640

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1405974 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1436370 (Python Code)

Max Activating Token Index: 592

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1408351 (Python Code)

Max Activating Token Index: 588

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1419935 (Python Code)

Max Activating Token Index: 643

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1599166 (Python Code)

Max Activating Token Index: 635

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1550347 (Python Code)

Max Activating Token Index: 582

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0054. Min Act: -0.0006

Data Index: 1334091 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1568484 (Python Code)

Max Activating Token Index: 599

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1564543 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1396652 (Python Code)

Max Activating Token Index: 639

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1366511 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1538177 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0051. Min Act: -0.0006

Data Index: 938079 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0050. Min Act: -0.0005

Data Index: 1630098 (Python Code)

Max Activating Token Index: 586

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0050. Min Act: -0.0005

Data Index: 1610775 (Python Code)

Max Activating Token Index: 717

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0050. Min Act: -0.0005

Data Index: 1578627 (Python Code)

Max Activating Token Index: 664

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0048. Min Act: -0.0005

Data Index: 1511859 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0050. Min Act: -0.0005

Data Index: 1651618 (Python Code)

Max Activating Token Index: 557