Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3338 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3279. Min Range: -2.3279

Max Act: 2.3279. Min Act: -0.0000

Data Index: 1325085 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.7191. Min Act: -0.0000

Data Index: 934032 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.3412. Min Act: -0.0000

Data Index: 756691 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1050261 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.3027. Min Act: -0.0000

Data Index: 12281 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.2402. Min Act: -0.0000

Data Index: 63611 (C4 (Web Text))

Max Activating Token Index: 373

Text #6

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1327602 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.2916. Min Act: -0.0000

Data Index: 427456 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1325194 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.1717. Min Act: -0.0000

Data Index: 1095938 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.0073. Min Act: -0.0000

Data Index: 101030 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.1318. Min Act: -0.0000

Data Index: 511611 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.1886. Min Act: -0.0000

Data Index: 942693 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.0154. Min Act: -0.0000

Data Index: 483743 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 2.3279. Min Range: -2.3279

Max Act: 1.0612. Min Act: -0.0000

Data Index: 313467 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 2.3279. Min Range: -2.3279

Max Act: 0.9930. Min Act: -0.0000

Data Index: 486893 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 2.3279. Min Range: -2.3279

Max Act: 0.9994. Min Act: -0.0000

Data Index: 276464 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 2.3279. Min Range: -2.3279

Max Act: 0.9942. Min Act: -0.0000

Data Index: 708479 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 2.3279. Min Range: -2.3279

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1176835 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 2.3279. Min Range: -2.3279

Max Act: 0.9894. Min Act: -0.0000

Data Index: 799092 (C4 (Web Text))

Max Activating Token Index: 180