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

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

Neuron 4631 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: 7.9565. Min Range: -7.9565

Max Act: 7.9565. Min Act: -0.0000

Data Index: 39215 (C4 (Web Text))

Max Activating Token Index: 954

Text #1

Max Range: 7.9565. Min Range: -7.9565

Max Act: 7.1593. Min Act: -0.0000

Data Index: 1142205 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 7.9565. Min Range: -7.9565

Max Act: 7.1821. Min Act: -0.0000

Data Index: 692477 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 7.9565. Min Range: -7.9565

Max Act: 7.3136. Min Act: -0.0000

Data Index: 1121658 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 7.9565. Min Range: -7.9565

Max Act: 6.9597. Min Act: -0.0000

Data Index: 948998 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 7.9565. Min Range: -7.9565

Max Act: 6.3843. Min Act: -0.0000

Data Index: 1282587 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 7.9565. Min Range: -7.9565

Max Act: 5.4537. Min Act: -0.0000

Data Index: 475192 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 7.9565. Min Range: -7.9565

Max Act: 5.7618. Min Act: -0.0000

Data Index: 654228 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 7.9565. Min Range: -7.9565

Max Act: 5.7204. Min Act: -0.0000

Data Index: 359998 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 7.9565. Min Range: -7.9565

Max Act: 5.2057. Min Act: -0.0000

Data Index: 231109 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 7.9565. Min Range: -7.9565

Max Act: 5.0942. Min Act: -0.0000

Data Index: 1278057 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 7.9565. Min Range: -7.9565

Max Act: 4.8894. Min Act: 0.0000

Data Index: 413384 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 7.9565. Min Range: -7.9565

Max Act: 5.3985. Min Act: -0.0000

Data Index: 1284852 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 7.9565. Min Range: -7.9565

Max Act: 4.9989. Min Act: 0.0000

Data Index: 508390 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 7.9565. Min Range: -7.9565

Max Act: 5.2748. Min Act: -0.0000

Data Index: 972336 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 7.9565. Min Range: -7.9565

Max Act: 4.7724. Min Act: -0.0000

Data Index: 257898 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 7.9565. Min Range: -7.9565

Max Act: 4.1622. Min Act: -0.0000

Data Index: 104846 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 7.9565. Min Range: -7.9565

Max Act: 4.1890. Min Act: -0.0000

Data Index: 675989 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 7.9565. Min Range: -7.9565

Max Act: 4.2449. Min Act: -0.0000

Data Index: 1117095 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 7.9565. Min Range: -7.9565

Max Act: 4.4362. Min Act: 0.0000

Data Index: 390752 (C4 (Web Text))

Max Activating Token Index: 921