Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1289 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1037. Min Range: -1.1037

Max Act: 1.0957. Min Act: -0.0000

Data Index: 593625 (The Pile)

Max Activating Token Index: 213

Text #1

Max Range: 1.1037. Min Range: -1.1037

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1228408 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.9407. Min Act: -0.0000

Data Index: 518522 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 1.1037. Min Range: -1.1037

Max Act: 1.0142. Min Act: -0.0000

Data Index: 517570 (The Pile)

Max Activating Token Index: 281

Text #4

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.9352. Min Act: -0.0000

Data Index: 1492828 (The Pile)

Max Activating Token Index: 985

Text #5

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1092911 (The Pile)

Max Activating Token Index: 1007

Text #6

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1478651 (The Pile)

Max Activating Token Index: 572

Text #7

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.9153. Min Act: -0.0000

Data Index: 1364654 (The Pile)

Max Activating Token Index: 501

Text #8

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8844. Min Act: -0.0000

Data Index: 685728 (The Pile)

Max Activating Token Index: 63

Text #9

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8459. Min Act: -0.0000

Data Index: 1913082 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1028910 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8161. Min Act: -0.0000

Data Index: 827288 (The Pile)

Max Activating Token Index: 478

Text #12

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8213. Min Act: -0.0000

Data Index: 635901 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8095. Min Act: -0.0000

Data Index: 965379 (The Pile)

Max Activating Token Index: 421

Text #14

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8032. Min Act: -0.0000

Data Index: 1427273 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8021. Min Act: -0.0000

Data Index: 95981 (The Pile)

Max Activating Token Index: 480

Text #16

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.8014. Min Act: -0.0000

Data Index: 727382 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.7805. Min Act: -0.0000

Data Index: 1141213 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1188411 (The Pile)

Max Activating Token Index: 694

Text #19

Max Range: 1.1037. Min Range: -1.1037

Max Act: 0.7146. Min Act: -0.0000

Data Index: 1954281 (The Pile)

Max Activating Token Index: 743