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

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

Neuron 779 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1211. Min Range: -3.1211

Max Act: 3.1211. Min Act: -0.0000

Data Index: 618117 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.8372. Min Act: -0.0000

Data Index: 922621 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.8734. Min Act: -0.0000

Data Index: 1081302 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.7456. Min Act: -0.0000

Data Index: 651628 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.6970. Min Act: -0.0000

Data Index: 1011116 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.4054. Min Act: -0.0000

Data Index: 867699 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.8219. Min Act: -0.0000

Data Index: 1310926 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.5256. Min Act: -0.0000

Data Index: 1587220 (Python Code)

Max Activating Token Index: 275

Text #8

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.4259. Min Act: -0.0000

Data Index: 822318 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.5143. Min Act: -0.0000

Data Index: 1637589 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.5181. Min Act: -0.0000

Data Index: 142858 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.3726. Min Act: -0.0000

Data Index: 688854 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.3649. Min Act: -0.0000

Data Index: 1314363 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.4857. Min Act: -0.0000

Data Index: 1449061 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.4339. Min Act: -0.0000

Data Index: 1251812 (C4 (Web Text))

Max Activating Token Index: 609

Text #15

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.5284. Min Act: -0.0000

Data Index: 1506443 (Python Code)

Max Activating Token Index: 769

Text #16

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.2774. Min Act: -0.0000

Data Index: 1145683 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.3911. Min Act: -0.0000

Data Index: 869986 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.3727. Min Act: -0.0000

Data Index: 880620 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 3.1211. Min Range: -3.1211

Max Act: 2.3844. Min Act: -0.0000

Data Index: 512566 (C4 (Web Text))

Max Activating Token Index: 316