Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2282 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0395. Min Range: -1.0395

Max Act: 1.0395. Min Act: -0.0004

Data Index: 902642 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 1.0395. Min Range: -1.0395

Max Act: 1.0273. Min Act: -0.0004

Data Index: 617869 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9846. Min Act: -0.0004

Data Index: 276285 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9907. Min Act: -0.0004

Data Index: 122892 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9828. Min Act: -0.0004

Data Index: 1073031 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9407. Min Act: -0.0004

Data Index: 989114 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9644. Min Act: -0.0004

Data Index: 961905 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 1.0395. Min Range: -1.0395

Max Act: 1.0091. Min Act: -0.0004

Data Index: 387529 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9174. Min Act: -0.0004

Data Index: 374258 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9064. Min Act: -0.0004

Data Index: 121017 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9914. Min Act: -0.0004

Data Index: 519070 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9328. Min Act: -0.0004

Data Index: 885480 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9278. Min Act: -0.0004

Data Index: 926447 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9186. Min Act: -0.0004

Data Index: 357608 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9153. Min Act: -0.0004

Data Index: 838560 (C4 (Web Text))

Max Activating Token Index: 9

Text #15

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8734. Min Act: -0.0004

Data Index: 218134 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8743. Min Act: -0.0004

Data Index: 180839 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9259. Min Act: -0.0004

Data Index: 638428 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.8586. Min Act: -0.0004

Data Index: 444353 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.0395. Min Range: -1.0395

Max Act: 0.9412. Min Act: -0.0004

Data Index: 1083114 (C4 (Web Text))

Max Activating Token Index: 210