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

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

Neuron 310 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: 0.8120. Min Range: -0.8120

Max Act: 0.8120. Min Act: -0.0000

Data Index: 268951 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7675. Min Act: -0.0000

Data Index: 755215 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.7046. Min Act: -0.0000

Data Index: 644501 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1051932 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6662. Min Act: -0.0000

Data Index: 721449 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6437. Min Act: -0.0000

Data Index: 782726 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.6329. Min Act: -0.0000

Data Index: 4265 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.5684. Min Act: -0.0000

Data Index: 244977 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.5799. Min Act: -0.0000

Data Index: 423366 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4983. Min Act: -0.0000

Data Index: 982881 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4981. Min Act: -0.0000

Data Index: 310390 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.5039. Min Act: -0.0000

Data Index: 1340800 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4966. Min Act: -0.0000

Data Index: 451632 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4648. Min Act: -0.0000

Data Index: 880109 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.5059. Min Act: -0.0000

Data Index: 814953 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4715. Min Act: 0.0000

Data Index: 761395 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4536. Min Act: -0.0000

Data Index: 983158 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4620. Min Act: -0.0000

Data Index: 507496 (C4 (Web Text))

Max Activating Token Index: 818

Text #18

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1075076 (C4 (Web Text))

Max Activating Token Index: 695

Text #19

Max Range: 0.8120. Min Range: -0.8120

Max Act: 0.4496. Min Act: -0.0000

Data Index: 12333 (C4 (Web Text))

Max Activating Token Index: 598