Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5752. Min Act: -0.0002

Data Index: 563175 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5689. Min Act: -0.0002

Data Index: 621137 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5139. Min Act: -0.0001

Data Index: 800852 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1359694 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5169. Min Act: -0.0002

Data Index: 1065527 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4294. Min Act: -0.0002

Data Index: 722251 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5589. Min Act: -0.0001

Data Index: 1306118 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5280. Min Act: -0.0002

Data Index: 290712 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5589. Min Act: -0.0001

Data Index: 758730 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5398. Min Act: -0.0002

Data Index: 99925 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5386. Min Act: -0.0002

Data Index: 1105268 (C4 (Web Text))

Max Activating Token Index: 884

Text #11

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5644. Min Act: -0.0002

Data Index: 179483 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5159. Min Act: -0.0002

Data Index: 412463 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5174. Min Act: -0.0002

Data Index: 1181386 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5269. Min Act: -0.0001

Data Index: 730359 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4931. Min Act: -0.0001

Data Index: 1194709 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5060. Min Act: -0.0002

Data Index: 1259727 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.5057. Min Act: -0.0002

Data Index: 24339 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4819. Min Act: -0.0002

Data Index: 678931 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.5752. Min Range: -0.5752

Max Act: 0.4871. Min Act: -0.0002

Data Index: 571632 (C4 (Web Text))

Max Activating Token Index: 534