Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 351 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.8892. Min Act: -0.0001

Data Index: 1088615 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7546. Min Act: -0.0001

Data Index: 1240270 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7436. Min Act: -0.0000

Data Index: 480018 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.7082. Min Act: -0.0000

Data Index: 749287 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6959. Min Act: -0.0000

Data Index: 406867 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6809. Min Act: -0.0000

Data Index: 29938 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6762. Min Act: -0.0000

Data Index: 771875 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1154684 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6649. Min Act: -0.0000

Data Index: 1313240 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6639. Min Act: -0.0001

Data Index: 746506 (C4 (Web Text))

Max Activating Token Index: 487

Text #10

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1061734 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6575. Min Act: -0.0000

Data Index: 1315787 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6312. Min Act: -0.0000

Data Index: 27604 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6502. Min Act: -0.0000

Data Index: 350326 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6688. Min Act: -0.0001

Data Index: 1355828 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6422. Min Act: -0.0000

Data Index: 68232 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6410. Min Act: -0.0000

Data Index: 521477 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1286128 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1066827 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 0.8892. Min Range: -0.8892

Max Act: 0.6144. Min Act: -0.0000

Data Index: 194054 (C4 (Web Text))

Max Activating Token Index: 937