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

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

Neuron 931 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9813. Min Act: -0.0000

Data Index: 591665 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1234758 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9298. Min Act: -0.0000

Data Index: 233200 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.9014. Min Act: -0.0000

Data Index: 394949 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8658. Min Act: -0.0000

Data Index: 604494 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1240002 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8784. Min Act: -0.0000

Data Index: 49533 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8379. Min Act: -0.0000

Data Index: 991272 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8182. Min Act: -0.0000

Data Index: 1048470 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8176. Min Act: -0.0000

Data Index: 220905 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7817. Min Act: -0.0000

Data Index: 732450 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8042. Min Act: -0.0000

Data Index: 952767 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1199344 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8004. Min Act: -0.0000

Data Index: 516113 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8164. Min Act: -0.0000

Data Index: 798257 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8079. Min Act: -0.0000

Data Index: 39394 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8275. Min Act: -0.0000

Data Index: 199534 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.8276. Min Act: -0.0000

Data Index: 789390 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7967. Min Act: -0.0000

Data Index: 1274622 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.9850. Min Range: -0.9850

Max Act: 0.7976. Min Act: -0.0000

Data Index: 182156 (C4 (Web Text))

Max Activating Token Index: 500