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

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

Neuron 4950 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.3984. Min Act: -0.0000

Data Index: 14263 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.3057. Min Act: -0.0000

Data Index: 412625 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1980. Min Act: -0.0000

Data Index: 452918 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1659. Min Act: -0.0000

Data Index: 650337 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2336. Min Act: -0.0000

Data Index: 49179 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 670

Text #6

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1092. Min Act: -0.0000

Data Index: 2691 (C4 (Web Text))

Max Activating Token Index: 948

Text #7

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.0391. Min Act: -0.0000

Data Index: 998284 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1408. Min Act: -0.0000

Data Index: 1655790 (Python Code)

Max Activating Token Index: 246

Text #9

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.0584. Min Act: -0.0000

Data Index: 481635 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1599078 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1507841 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1475370 (Python Code)

Max Activating Token Index: 82

Text #13

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.9624. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1587642 (Python Code)

Max Activating Token Index: 344

Text #15

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1561395 (Python Code)

Max Activating Token Index: 128

Text #16

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1076882 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1621245 (Python Code)

Max Activating Token Index: 290

Text #18

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.8600. Min Act: -0.0000

Data Index: 261145 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.3984. Min Range: -1.3984

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1580586 (Python Code)

Max Activating Token Index: 688