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

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

Neuron 1907 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: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 526806 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0904. Min Act: -0.0000

Data Index: 236738 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0868. Min Act: -0.0000

Data Index: 813585 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1030346 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0847. Min Act: -0.0000

Data Index: 645874 (C4 (Web Text))

Max Activating Token Index: 985

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0842. Min Act: -0.0000

Data Index: 825301 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0773. Min Act: -0.0000

Data Index: 74560 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0752. Min Act: -0.0000

Data Index: 966302 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0745. Min Act: -0.0001

Data Index: 562630 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0746. Min Act: -0.0000

Data Index: 161546 (C4 (Web Text))

Max Activating Token Index: 732

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0678. Min Act: -0.0001

Data Index: 522885 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1151282 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0692. Min Act: -0.0001

Data Index: 75092 (C4 (Web Text))

Max Activating Token Index: 1021

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0705. Min Act: -0.0000

Data Index: 134771 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0680. Min Act: -0.0000

Data Index: 397553 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0729. Min Act: -0.0001

Data Index: 272852 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0696. Min Act: -0.0000

Data Index: 418328 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0697. Min Act: -0.0000

Data Index: 232300 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0702. Min Act: -0.0001

Data Index: 866100 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1344492 (C4 (Web Text))

Max Activating Token Index: 119