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

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

Neuron 2541 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3089. Min Range: -3.3089

Max Act: 3.3089. Min Act: -0.0000

Data Index: 1483669 (Python Code)

Max Activating Token Index: 38

Text #1

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.9646. Min Act: -0.0000

Data Index: 1625834 (Python Code)

Max Activating Token Index: 528

Text #2

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.5452. Min Act: -0.0000

Data Index: 1414206 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.5017. Min Act: -0.0000

Data Index: 1455649 (Python Code)

Max Activating Token Index: 701

Text #4

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.2954. Min Act: -0.0000

Data Index: 1470577 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 3.3089. Min Range: -3.3089

Max Act: 2.1110. Min Act: -0.0000

Data Index: 1548937 (Python Code)

Max Activating Token Index: 754

Text #6

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.8418. Min Act: -0.0000

Data Index: 1438049 (Python Code)

Max Activating Token Index: 86

Text #7

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.9383. Min Act: -0.0000

Data Index: 1496013 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.7231. Min Act: -0.0000

Data Index: 1617505 (Python Code)

Max Activating Token Index: 237

Text #9

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.7628. Min Act: -0.0000

Data Index: 1582235 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.8136. Min Act: -0.0000

Data Index: 1596882 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.7074. Min Act: -0.0000

Data Index: 1546948 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.6884. Min Act: -0.0000

Data Index: 1462938 (Python Code)

Max Activating Token Index: 36

Text #13

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.7505. Min Act: -0.0000

Data Index: 1397644 (Python Code)

Max Activating Token Index: 657

Text #14

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.6302. Min Act: -0.0000

Data Index: 1174129 (C4 (Web Text))

Max Activating Token Index: 162

Text #15

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.6670. Min Act: -0.0000

Data Index: 1588487 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.7612. Min Act: -0.0000

Data Index: 249141 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.7133. Min Act: -0.0000

Data Index: 1391853 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1427908 (Python Code)

Max Activating Token Index: 451

Text #19

Max Range: 3.3089. Min Range: -3.3089

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1533984 (Python Code)

Max Activating Token Index: 872