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

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

Neuron 4493 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: 3.7522. Min Range: -3.7522

Max Act: 3.7522. Min Act: -0.0000

Data Index: 812418 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.2095. Min Act: -0.0000

Data Index: 893353 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 3.7522. Min Range: -3.7522

Max Act: 3.0133. Min Act: -0.0000

Data Index: 1082544 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.8164. Min Act: -0.0000

Data Index: 77929 (C4 (Web Text))

Max Activating Token Index: 18

Text #4

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.6043. Min Act: -0.0000

Data Index: 116583 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.7896. Min Act: -0.0000

Data Index: 470184 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.6345. Min Act: -0.0000

Data Index: 755788 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.4690. Min Act: -0.0000

Data Index: 1291590 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.1935. Min Act: -0.0000

Data Index: 1175649 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.4249. Min Act: -0.0000

Data Index: 673913 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.5618. Min Act: -0.0000

Data Index: 1442681 (Python Code)

Max Activating Token Index: 550

Text #11

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.6368. Min Act: -0.0000

Data Index: 742885 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.4946. Min Act: -0.0000

Data Index: 753069 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.4530. Min Act: -0.0000

Data Index: 100257 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.5800. Min Act: -0.0000

Data Index: 395067 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.2974. Min Act: -0.0000

Data Index: 201649 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.4324. Min Act: -0.0000

Data Index: 837534 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.2602. Min Act: -0.0000

Data Index: 539276 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.3588. Min Act: -0.0000

Data Index: 564814 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 3.7522. Min Range: -3.7522

Max Act: 2.3465. Min Act: -0.0000

Data Index: 526877 (C4 (Web Text))

Max Activating Token Index: 24