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

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

Neuron 5267 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: 1.4544. Min Range: -1.4544

Max Act: 1.4544. Min Act: -0.0000

Data Index: 1212507 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1355256 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1050202 (C4 (Web Text))

Max Activating Token Index: 114

Text #3

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.3732. Min Act: -0.0000

Data Index: 546250 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.1802. Min Act: -0.0000

Data Index: 809415 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.1627. Min Act: 0.0000

Data Index: 210201 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0582. Min Act: -0.0000

Data Index: 850776 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0003. Min Act: -0.0000

Data Index: 1288713 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9825. Min Act: -0.0000

Data Index: 435005 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9751. Min Act: -0.0000

Data Index: 405091 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1086203 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1098806 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9455. Min Act: -0.0000

Data Index: 927588 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9337. Min Act: -0.0000

Data Index: 850689 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 1.4544. Min Range: -1.4544

Max Act: 1.0022. Min Act: -0.0000

Data Index: 638608 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9444. Min Act: -0.0000

Data Index: 1039693 (C4 (Web Text))

Max Activating Token Index: 839

Text #16

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.8582. Min Act: -0.0000

Data Index: 117890 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.9341. Min Act: -0.0000

Data Index: 784350 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.8712. Min Act: 0.0000

Data Index: 1253648 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 1.4544. Min Range: -1.4544

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1038774 (C4 (Web Text))

Max Activating Token Index: 756