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

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

Neuron 5352 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: 3.0731. Min Range: -3.0731

Max Act: 3.0731. Min Act: -0.0000

Data Index: 149692 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 3.0731. Min Range: -3.0731

Max Act: 3.0438. Min Act: -0.0000

Data Index: 1070350 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 3.0731. Min Range: -3.0731

Max Act: 3.0080. Min Act: -0.0000

Data Index: 1346429 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.7236. Min Act: -0.0000

Data Index: 1203710 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.6841. Min Act: -0.0000

Data Index: 318907 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5480. Min Act: -0.0000

Data Index: 855018 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5363. Min Act: -0.0000

Data Index: 425207 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5329. Min Act: -0.0000

Data Index: 259012 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.6486. Min Act: -0.0000

Data Index: 276066 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.7651. Min Act: -0.0000

Data Index: 690000 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.7472. Min Act: -0.0000

Data Index: 270535 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.7250. Min Act: -0.0000

Data Index: 634802 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5848. Min Act: -0.0000

Data Index: 796506 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.5656. Min Act: -0.0000

Data Index: 75867 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4194. Min Act: -0.0000

Data Index: 189579 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4565. Min Act: -0.0000

Data Index: 780201 (C4 (Web Text))

Max Activating Token Index: 415

Text #16

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4631. Min Act: -0.0000

Data Index: 210694 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4331. Min Act: -0.0000

Data Index: 990958 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4037. Min Act: -0.0000

Data Index: 595760 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 3.0731. Min Range: -3.0731

Max Act: 2.4033. Min Act: -0.0000

Data Index: 1321605 (C4 (Web Text))

Max Activating Token Index: 746