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

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

Neuron 3456 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0336. Min Range: -1.0336

Max Act: 1.0336. Min Act: -0.0001

Data Index: 436355 (C4 (Web Text))

Max Activating Token Index: 904

Text #1

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7685. Min Act: -0.0000

Data Index: 642195 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7318. Min Act: -0.0000

Data Index: 605709 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7829. Min Act: -0.0001

Data Index: 436092 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7310. Min Act: -0.0000

Data Index: 1240487 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7498. Min Act: -0.0000

Data Index: 503124 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7474. Min Act: -0.0000

Data Index: 974790 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7267. Min Act: -0.0001

Data Index: 465671 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7129. Min Act: -0.0000

Data Index: 230599 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7117. Min Act: -0.0000

Data Index: 32604 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7717. Min Act: -0.0001

Data Index: 1341993 (C4 (Web Text))

Max Activating Token Index: 632

Text #11

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7335. Min Act: -0.0001

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7270. Min Act: -0.0001

Data Index: 553955 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7256. Min Act: -0.0000

Data Index: 230253 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.6998. Min Act: -0.0000

Data Index: 123149 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.6795. Min Act: -0.0001

Data Index: 464099 (C4 (Web Text))

Max Activating Token Index: 1002

Text #16

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7403. Min Act: -0.0000

Data Index: 1180743 (C4 (Web Text))

Max Activating Token Index: 679

Text #17

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7146. Min Act: -0.0000

Data Index: 775102 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.6912. Min Act: -0.0000

Data Index: 1098473 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 1.0336. Min Range: -1.0336

Max Act: 0.7050. Min Act: -0.0000

Data Index: 432154 (C4 (Web Text))

Max Activating Token Index: 758