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

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

Neuron 5555 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0142. Min Range: -2.0142

Max Act: 2.0142. Min Act: -0.0000

Data Index: 42272 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.6121. Min Act: -0.0000

Data Index: 911713 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.5990. Min Act: -0.0000

Data Index: 95577 (C4 (Web Text))

Max Activating Token Index: 238

Text #3

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.5875. Min Act: -0.0000

Data Index: 934526 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.6663. Min Act: -0.0000

Data Index: 471777 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.6619. Min Act: -0.0000

Data Index: 81718 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.5568. Min Act: -0.0000

Data Index: 1321203 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4992. Min Act: -0.0000

Data Index: 123999 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4904. Min Act: -0.0000

Data Index: 69026 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.5402. Min Act: 0.0000

Data Index: 1359003 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4548. Min Act: -0.0000

Data Index: 362191 (C4 (Web Text))

Max Activating Token Index: 613

Text #11

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.6236. Min Act: -0.0000

Data Index: 321165 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.5326. Min Act: -0.0000

Data Index: 590686 (C4 (Web Text))

Max Activating Token Index: 410

Text #13

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4264. Min Act: -0.0000

Data Index: 771032 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4946. Min Act: -0.0000

Data Index: 5343 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4696. Min Act: -0.0000

Data Index: 662623 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4587. Min Act: -0.0000

Data Index: 684802 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.3739. Min Act: -0.0000

Data Index: 645785 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.5337. Min Act: -0.0000

Data Index: 472619 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 2.0142. Min Range: -2.0142

Max Act: 1.4506. Min Act: -0.0000

Data Index: 151429 (C4 (Web Text))

Max Activating Token Index: 426