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

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

Neuron 3727 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1250. Min Range: -2.1250

Max Act: 2.1085. Min Act: -0.0000

Data Index: 951895 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 2.1250. Min Range: -2.1250

Max Act: 2.1250. Min Act: -0.0000

Data Index: 33428 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.7870. Min Act: -0.0000

Data Index: 663855 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.7831. Min Act: -0.0000

Data Index: 199193 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.6848. Min Act: -0.0000

Data Index: 893800 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.6009. Min Act: -0.0000

Data Index: 891436 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.8240. Min Act: -0.0000

Data Index: 519865 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.7726. Min Act: -0.0000

Data Index: 861966 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.7067. Min Act: -0.0000

Data Index: 300529 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.7899. Min Act: -0.0000

Data Index: 508270 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.5604. Min Act: -0.0000

Data Index: 904555 (C4 (Web Text))

Max Activating Token Index: 844

Text #11

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1301937 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.5980. Min Act: -0.0000

Data Index: 1340767 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.6064. Min Act: -0.0000

Data Index: 638851 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.6028. Min Act: -0.0000

Data Index: 358735 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.4828. Min Act: -0.0000

Data Index: 552834 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.3819. Min Act: -0.0000

Data Index: 651374 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.5346. Min Act: -0.0000

Data Index: 845127 (C4 (Web Text))

Max Activating Token Index: 131

Text #18

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.3507. Min Act: -0.0000

Data Index: 553907 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 2.1250. Min Range: -2.1250

Max Act: 1.5215. Min Act: -0.0000

Data Index: 536244 (C4 (Web Text))

Max Activating Token Index: 573