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

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

Neuron 2013 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1141. Min Range: -1.1141

Max Act: 1.1141. Min Act: -0.0001

Data Index: 323313 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 1.1141. Min Range: -1.1141

Max Act: 1.1066. Min Act: -0.0001

Data Index: 1184548 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8901. Min Act: -0.0001

Data Index: 1115761 (C4 (Web Text))

Max Activating Token Index: 370

Text #3

Max Range: 1.1141. Min Range: -1.1141

Max Act: 1.0030. Min Act: -0.0001

Data Index: 80924 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9623. Min Act: -0.0001

Data Index: 12541 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9351. Min Act: -0.0001

Data Index: 416860 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 1.1141. Min Range: -1.1141

Max Act: 1.0294. Min Act: -0.0001

Data Index: 569068 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8181. Min Act: -0.0001

Data Index: 557956 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9571. Min Act: -0.0001

Data Index: 366366 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9479. Min Act: -0.0001

Data Index: 436154 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.8132. Min Act: -0.0001

Data Index: 320506 (C4 (Web Text))

Max Activating Token Index: 623

Text #11

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9462. Min Act: -0.0001

Data Index: 489037 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9162. Min Act: -0.0001

Data Index: 1081620 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9403. Min Act: -0.0001

Data Index: 1001649 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9068. Min Act: -0.0001

Data Index: 939113 (C4 (Web Text))

Max Activating Token Index: 287

Text #15

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9039. Min Act: -0.0001

Data Index: 1275326 (C4 (Web Text))

Max Activating Token Index: 404

Text #16

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9025. Min Act: -0.0001

Data Index: 9933 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9309. Min Act: -0.0001

Data Index: 370196 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.7749. Min Act: -0.0001

Data Index: 35748 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 1.1141. Min Range: -1.1141

Max Act: 0.9490. Min Act: -0.0001

Data Index: 350533 (C4 (Web Text))

Max Activating Token Index: 864