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

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

Neuron 4103 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: 3.4450. Min Range: -3.4450

Max Act: 3.2031. Min Act: -0.0000

Data Index: 962665 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.4450. Min Act: -0.0000

Data Index: 909628 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.9163. Min Act: -0.0000

Data Index: 1014062 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7076. Min Act: -0.0000

Data Index: 392586 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.9177. Min Act: -0.0000

Data Index: 890875 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.8815. Min Act: -0.0000

Data Index: 77639 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.8936. Min Act: -0.0000

Data Index: 969398 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.9805. Min Act: -0.0000

Data Index: 1016243 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7125. Min Act: -0.0000

Data Index: 226079 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.8431. Min Act: -0.0000

Data Index: 896344 (C4 (Web Text))

Max Activating Token Index: 894

Text #10

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7050. Min Act: -0.0000

Data Index: 610112 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.6336. Min Act: -0.0000

Data Index: 20645 (C4 (Web Text))

Max Activating Token Index: 468

Text #12

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7639. Min Act: -0.0000

Data Index: 1085136 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.8744. Min Act: -0.0000

Data Index: 782569 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7151. Min Act: -0.0000

Data Index: 561003 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7586. Min Act: -0.0000

Data Index: 115437 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 3.4450. Min Range: -3.4450

Max Act: 3.0132. Min Act: -0.0000

Data Index: 483080 (C4 (Web Text))

Max Activating Token Index: 746

Text #17

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.6953. Min Act: -0.0000

Data Index: 931096 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7119. Min Act: -0.0000

Data Index: 982286 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 3.4450. Min Range: -3.4450

Max Act: 2.7069. Min Act: -0.0000

Data Index: 1280289 (C4 (Web Text))

Max Activating Token Index: 963