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

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

Neuron 3498 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4933. Min Range: -5.4933

Max Act: 5.4933. Min Act: -0.0000

Data Index: 792161 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 5.4933. Min Range: -5.4933

Max Act: 5.2841. Min Act: -0.0000

Data Index: 705136 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 5.4933. Min Range: -5.4933

Max Act: 5.1232. Min Act: -0.0000

Data Index: 94602 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 5.4933. Min Range: -5.4933

Max Act: 5.0379. Min Act: -0.0000

Data Index: 777116 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.4408. Min Act: -0.0000

Data Index: 913683 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.9434. Min Act: -0.0000

Data Index: 916408 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.7675. Min Act: -0.0000

Data Index: 1295772 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.4133. Min Act: -0.0000

Data Index: 684339 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.7523. Min Act: -0.0000

Data Index: 555765 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.5355. Min Act: -0.0000

Data Index: 1153043 (C4 (Web Text))

Max Activating Token Index: 618

Text #10

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.6484. Min Act: -0.0000

Data Index: 566641 (C4 (Web Text))

Max Activating Token Index: 186

Text #11

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.6851. Min Act: -0.0000

Data Index: 1258411 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.2909. Min Act: -0.0000

Data Index: 1086853 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.0989. Min Act: -0.0000

Data Index: 468163 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.4141. Min Act: -0.0000

Data Index: 114138 (C4 (Web Text))

Max Activating Token Index: 574

Text #15

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.5734. Min Act: -0.0000

Data Index: 460172 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.5327. Min Act: -0.0000

Data Index: 872097 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.9235. Min Act: -0.0000

Data Index: 244692 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.5491. Min Act: -0.0000

Data Index: 1118789 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 5.4933. Min Range: -5.4933

Max Act: 4.5105. Min Act: -0.0000

Data Index: 1082478 (C4 (Web Text))

Max Activating Token Index: 524