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

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

Neuron 4097 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.3619. Min Act: -0.0000

Data Index: 1309754 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1879. Min Act: -0.0000

Data Index: 646081 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.1395. Min Act: -0.0000

Data Index: 440820 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0252. Min Act: -0.0000

Data Index: 284619 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.8642. Min Act: -0.0000

Data Index: 1070333 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 2.3619. Min Range: -2.3619

Max Act: 2.0781. Min Act: -0.0000

Data Index: 309300 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.9188. Min Act: -0.0000

Data Index: 126236 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.8169. Min Act: -0.0000

Data Index: 154894 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.7729. Min Act: -0.0000

Data Index: 429849 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.7479. Min Act: -0.0000

Data Index: 1271246 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.8529. Min Act: -0.0000

Data Index: 1331595 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.7456. Min Act: -0.0000

Data Index: 1269392 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1221997 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.5740. Min Act: -0.0000

Data Index: 552066 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.6571. Min Act: -0.0000

Data Index: 501310 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.6222. Min Act: -0.0000

Data Index: 614297 (C4 (Web Text))

Max Activating Token Index: 105

Text #16

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.5151. Min Act: -0.0000

Data Index: 540345 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.6040. Min Act: -0.0000

Data Index: 1341213 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.4955. Min Act: -0.0000

Data Index: 723907 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 2.3619. Min Range: -2.3619

Max Act: 1.5783. Min Act: -0.0000

Data Index: 1088762 (C4 (Web Text))

Max Activating Token Index: 169