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

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

Neuron 2632 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2149. Min Range: -2.2149

Max Act: 2.0227. Min Act: -0.0000

Data Index: 876973 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.2149. Min Range: -2.2149

Max Act: 2.2149. Min Act: -0.0000

Data Index: 486052 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 2.2149. Min Range: -2.2149

Max Act: 2.0776. Min Act: -0.0000

Data Index: 51366 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.9904. Min Act: -0.0000

Data Index: 134380 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.9861. Min Act: -0.0000

Data Index: 578688 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.9738. Min Act: -0.0000

Data Index: 1012849 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 2.2149. Min Range: -2.2149

Max Act: 2.0344. Min Act: -0.0000

Data Index: 524211 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.8530. Min Act: -0.0000

Data Index: 291785 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.7741. Min Act: -0.0000

Data Index: 856490 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.8476. Min Act: -0.0000

Data Index: 586723 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.8620. Min Act: -0.0000

Data Index: 70398 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.7564. Min Act: -0.0000

Data Index: 874169 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.6905. Min Act: -0.0000

Data Index: 1306159 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.8002. Min Act: -0.0000

Data Index: 905822 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.9996. Min Act: -0.0000

Data Index: 76604 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.7894. Min Act: -0.0000

Data Index: 526215 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1120543 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.7775. Min Act: -0.0000

Data Index: 761470 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.8268. Min Act: -0.0000

Data Index: 814103 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 2.2149. Min Range: -2.2149

Max Act: 1.7423. Min Act: -0.0000

Data Index: 800623 (C4 (Web Text))

Max Activating Token Index: 475