Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2486 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.0616. Min Act: -0.0000

Data Index: 939290 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.1302. Min Act: -0.0000

Data Index: 269769 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.1280. Min Act: -0.0000

Data Index: 345891 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.1492. Min Act: -0.0000

Data Index: 1253231 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.1295. Min Act: -0.0000

Data Index: 1141610 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.0629. Min Act: -0.0000

Data Index: 524594 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.0155. Min Act: -0.0000

Data Index: 411769 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.0430. Min Act: -0.0000

Data Index: 1193026 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.0298. Min Act: -0.0000

Data Index: 789767 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9788. Min Act: -0.0000

Data Index: 476270 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.0096. Min Act: -0.0000

Data Index: 987672 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.1492. Min Range: -1.1492

Max Act: 1.0125. Min Act: -0.0000

Data Index: 752954 (C4 (Web Text))

Max Activating Token Index: 189

Text #12

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1222975 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8750. Min Act: -0.0000

Data Index: 142099 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1126533 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.9347. Min Act: -0.0000

Data Index: 1129498 (C4 (Web Text))

Max Activating Token Index: 952

Text #16

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8404. Min Act: -0.0000

Data Index: 90031 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8813. Min Act: -0.0000

Data Index: 281445 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1259850 (C4 (Web Text))

Max Activating Token Index: 473

Text #19

Max Range: 1.1492. Min Range: -1.1492

Max Act: 0.8409. Min Act: -0.0000

Data Index: 1256569 (C4 (Web Text))

Max Activating Token Index: 314