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

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

Neuron 3469 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.9886. Min Act: -0.0000

Data Index: 988460 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.6019. Min Act: -0.0000

Data Index: 923587 (C4 (Web Text))

Max Activating Token Index: 172

Text #2

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.4749. Min Act: -0.0000

Data Index: 307512 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 2.9886. Min Range: -2.9886

Max Act: 2.0547. Min Act: -0.0000

Data Index: 1209214 (C4 (Web Text))

Max Activating Token Index: 579

Text #4

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.6147. Min Act: -0.0000

Data Index: 480197 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.7026. Min Act: -0.0000

Data Index: 77915 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.6420. Min Act: -0.0000

Data Index: 1054117 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.5563. Min Act: -0.0000

Data Index: 73111 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.4688. Min Act: -0.0000

Data Index: 183299 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.5400. Min Act: -0.0000

Data Index: 454692 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.5365. Min Act: -0.0000

Data Index: 560714 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.4838. Min Act: -0.0000

Data Index: 558898 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.3010. Min Act: -0.0000

Data Index: 457948 (C4 (Web Text))

Max Activating Token Index: 196

Text #13

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.3920. Min Act: -0.0000

Data Index: 666980 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.2899. Min Act: -0.0000

Data Index: 218096 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.3693. Min Act: -0.0000

Data Index: 402987 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.2907. Min Act: -0.0000

Data Index: 181556 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1892 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.4843. Min Act: -0.0000

Data Index: 1244879 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 2.9886. Min Range: -2.9886

Max Act: 1.3286. Min Act: -0.0000

Data Index: 1218031 (C4 (Web Text))

Max Activating Token Index: 858