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

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

Neuron 2217 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3512. Min Range: -2.3512

Max Act: 2.3512. Min Act: -0.0000

Data Index: 48212 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 2.3512. Min Range: -2.3512

Max Act: 2.0268. Min Act: -0.0000

Data Index: 223701 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.9891. Min Act: -0.0000

Data Index: 844431 (C4 (Web Text))

Max Activating Token Index: 571

Text #3

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.7882. Min Act: -0.0000

Data Index: 246892 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.7910. Min Act: -0.0000

Data Index: 261034 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.7415. Min Act: -0.0000

Data Index: 1082742 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.7318. Min Act: -0.0000

Data Index: 13605 (C4 (Web Text))

Max Activating Token Index: 547

Text #7

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.6449. Min Act: -0.0000

Data Index: 877536 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.5820. Min Act: -0.0000

Data Index: 680992 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.5387. Min Act: -0.0000

Data Index: 729454 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.6415. Min Act: -0.0000

Data Index: 1036432 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.5005. Min Act: -0.0000

Data Index: 751734 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.4099. Min Act: -0.0000

Data Index: 266478 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.3119. Min Act: -0.0000

Data Index: 781572 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1575307 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.4497. Min Act: 0.0000

Data Index: 1191602 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.3781. Min Act: -0.0000

Data Index: 1416247 (Python Code)

Max Activating Token Index: 701

Text #17

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.3115. Min Act: -0.0000

Data Index: 1195546 (C4 (Web Text))

Max Activating Token Index: 556

Text #18

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.2856. Min Act: -0.0000

Data Index: 278881 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 2.3512. Min Range: -2.3512

Max Act: 1.3130. Min Act: -0.0000

Data Index: 289660 (C4 (Web Text))

Max Activating Token Index: 641