Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.7970. Min Act: -0.0001

Data Index: 249592 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.2607. Min Act: -0.0001

Data Index: 1333460 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1096. Min Act: -0.0001

Data Index: 507829 (C4 (Web Text))

Max Activating Token Index: 491

Text #3

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1507. Min Act: -0.0001

Data Index: 286446 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.1867. Min Act: -0.0001

Data Index: 1170520 (C4 (Web Text))

Max Activating Token Index: 371

Text #5

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0849. Min Act: -0.0001

Data Index: 814402 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0729. Min Act: -0.0001

Data Index: 1192011 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0765. Min Act: -0.0001

Data Index: 146599 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0231. Min Act: -0.0001

Data Index: 865141 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9836. Min Act: -0.0001

Data Index: 763377 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0736. Min Act: -0.0001

Data Index: 1262209 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9730. Min Act: -0.0001

Data Index: 72793 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9508. Min Act: -0.0001

Data Index: 221473 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 1.7970. Min Range: -1.7970

Max Act: 1.0284. Min Act: -0.0001

Data Index: 856672 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9338. Min Act: -0.0001

Data Index: 754718 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9053. Min Act: -0.0001

Data Index: 390906 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9616. Min Act: -0.0001

Data Index: 419490 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9942. Min Act: -0.0001

Data Index: 41356 (C4 (Web Text))

Max Activating Token Index: 245

Text #18

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9023. Min Act: -0.0001

Data Index: 723253 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 1.7970. Min Range: -1.7970

Max Act: 0.9351. Min Act: -0.0001

Data Index: 30956 (C4 (Web Text))

Max Activating Token Index: 515