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

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

Neuron 5538 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: 3.9112. Min Range: -3.9112

Max Act: 3.9112. Min Act: -0.0000

Data Index: 260765 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.5285. Min Act: -0.0000

Data Index: 1543091 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 3.9112. Min Range: -3.9112

Max Act: 3.1515. Min Act: -0.0000

Data Index: 57775 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.9738. Min Act: -0.0000

Data Index: 1207684 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.8749. Min Act: -0.0000

Data Index: 78998 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.8339. Min Act: -0.0000

Data Index: 1079784 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.8398. Min Act: -0.0000

Data Index: 869558 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.6969. Min Act: -0.0000

Data Index: 1564667 (Python Code)

Max Activating Token Index: 190

Text #8

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.7231. Min Act: -0.0000

Data Index: 1484896 (Python Code)

Max Activating Token Index: 24

Text #9

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.4962. Min Act: -0.0000

Data Index: 1361792 (Python Code)

Max Activating Token Index: 647

Text #10

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.7064. Min Act: -0.0000

Data Index: 749031 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.5419. Min Act: -0.0000

Data Index: 279991 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.6901. Min Act: -0.0000

Data Index: 1375202 (Python Code)

Max Activating Token Index: 636

Text #13

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.6089. Min Act: -0.0000

Data Index: 342164 (C4 (Web Text))

Max Activating Token Index: 934

Text #14

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.3656. Min Act: -0.0000

Data Index: 306234 (C4 (Web Text))

Max Activating Token Index: 44

Text #15

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.4815. Min Act: -0.0000

Data Index: 576975 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.4765. Min Act: -0.0000

Data Index: 1001433 (C4 (Web Text))

Max Activating Token Index: 209

Text #17

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.5731. Min Act: -0.0000

Data Index: 688025 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.4143. Min Act: -0.0000

Data Index: 534964 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 3.9112. Min Range: -3.9112

Max Act: 2.4866. Min Act: -0.0000

Data Index: 1641262 (Python Code)

Max Activating Token Index: 361