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

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

Neuron 1924 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2276. Min Range: -6.2276

Max Act: 6.2276. Min Act: -0.0000

Data Index: 1138058 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 6.2276. Min Range: -6.2276

Max Act: 5.3536. Min Act: -0.0000

Data Index: 592643 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 6.2276. Min Range: -6.2276

Max Act: 5.1751. Min Act: -0.0000

Data Index: 993702 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.3902. Min Act: -0.0000

Data Index: 365513 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.3154. Min Act: -0.0000

Data Index: 333170 (C4 (Web Text))

Max Activating Token Index: 798

Text #5

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.4823. Min Act: -0.0000

Data Index: 289930 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.2442. Min Act: -0.0000

Data Index: 62293 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.2052. Min Act: -0.0000

Data Index: 781837 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.2215. Min Act: -0.0000

Data Index: 1155634 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.0104. Min Act: -0.0000

Data Index: 829612 (C4 (Web Text))

Max Activating Token Index: 778

Text #10

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.1796. Min Act: -0.0000

Data Index: 1312509 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.1606. Min Act: -0.0000

Data Index: 80478 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.2551. Min Act: -0.0000

Data Index: 278816 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.0523. Min Act: -0.0000

Data Index: 843164 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 6.2276. Min Range: -6.2276

Max Act: 3.9997. Min Act: -0.0000

Data Index: 384485 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.2726. Min Act: -0.0000

Data Index: 243772 (C4 (Web Text))

Max Activating Token Index: 868

Text #16

Max Range: 6.2276. Min Range: -6.2276

Max Act: 3.9251. Min Act: -0.0000

Data Index: 321683 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 6.2276. Min Range: -6.2276

Max Act: 4.0890. Min Act: -0.0000

Data Index: 775010 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 6.2276. Min Range: -6.2276

Max Act: 3.7843. Min Act: -0.0000

Data Index: 252967 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 6.2276. Min Range: -6.2276

Max Act: 3.6735. Min Act: -0.0000

Data Index: 447274 (C4 (Web Text))

Max Activating Token Index: 529