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

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

Neuron 4117 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.4513. Min Act: -0.0000

Data Index: 403405 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.3198. Min Act: -0.0000

Data Index: 301868 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2981. Min Act: -0.0000

Data Index: 755820 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2807. Min Act: -0.0000

Data Index: 114323 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2779. Min Act: -0.0000

Data Index: 1179147 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2864. Min Act: -0.0000

Data Index: 129860 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2739. Min Act: 0.0000

Data Index: 1312192 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2830. Min Act: -0.0000

Data Index: 1162202 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1209742 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1155906 (C4 (Web Text))

Max Activating Token Index: 702

Text #10

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1098366 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2700. Min Act: -0.0000

Data Index: 120707 (C4 (Web Text))

Max Activating Token Index: 352

Text #12

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2811. Min Act: -0.0000

Data Index: 169170 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2778. Min Act: -0.0000

Data Index: 1351704 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2681. Min Act: -0.0000

Data Index: 50186 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1027829 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2643. Min Act: -0.0000

Data Index: 333068 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2429. Min Act: -0.0000

Data Index: 82743 (C4 (Web Text))

Max Activating Token Index: 807

Text #18

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1252475 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.4513. Min Range: -0.4513

Max Act: 0.2642. Min Act: -0.0000

Data Index: 1232344 (C4 (Web Text))

Max Activating Token Index: 431