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

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

Neuron 3333 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: 1.3104. Min Range: -1.3104

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1002023 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.2996. Min Act: -0.0000

Data Index: 515911 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.2624. Min Act: -0.0000

Data Index: 492422 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.1619. Min Act: -0.0000

Data Index: 40978 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8201. Min Act: -0.0000

Data Index: 391157 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 1.3104. Min Range: -1.3104

Max Act: 1.0906. Min Act: -0.0000

Data Index: 1103576 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1084948 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9691. Min Act: -0.0000

Data Index: 1209151 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8802. Min Act: -0.0000

Data Index: 422051 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9624. Min Act: -0.0000

Data Index: 962742 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8658. Min Act: -0.0000

Data Index: 237766 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8547. Min Act: -0.0000

Data Index: 58625 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1347958 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.7730. Min Act: -0.0000

Data Index: 1032608 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8264. Min Act: -0.0000

Data Index: 31641 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.9499. Min Act: -0.0000

Data Index: 723206 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.7867. Min Act: -0.0000

Data Index: 1107471 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8131. Min Act: -0.0000

Data Index: 612618 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.7662. Min Act: -0.0000

Data Index: 629970 (C4 (Web Text))

Max Activating Token Index: 612

Text #19

Max Range: 1.3104. Min Range: -1.3104

Max Act: 0.8049. Min Act: -0.0000

Data Index: 1202537 (C4 (Web Text))

Max Activating Token Index: 491