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

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

Neuron 5566 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1526. Min Act: -0.0002

Data Index: 1590617 (Python Code)

Max Activating Token Index: 700

Text #1

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1510997 (Python Code)

Max Activating Token Index: 122

Text #2

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1418784 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1610364 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1505343 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1425997 (Python Code)

Max Activating Token Index: 763

Text #6

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1394173 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1647862 (Python Code)

Max Activating Token Index: 565

Text #8

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1175. Min Act: -0.0002

Data Index: 1545690 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1560998 (Python Code)

Max Activating Token Index: 475

Text #10

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1554774 (Python Code)

Max Activating Token Index: 798

Text #11

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1532696 (Python Code)

Max Activating Token Index: 406

Text #12

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1116. Min Act: -0.0002

Data Index: 1386597 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1561694 (Python Code)

Max Activating Token Index: 619

Text #14

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1101. Min Act: -0.0002

Data Index: 1644907 (Python Code)

Max Activating Token Index: 928

Text #15

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1046. Min Act: -0.0002

Data Index: 1572331 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1050. Min Act: -0.0003

Data Index: 1550948 (Python Code)

Max Activating Token Index: 490

Text #17

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1583160 (Python Code)

Max Activating Token Index: 975

Text #18

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1073. Min Act: -0.0002

Data Index: 1514639 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 0.1526. Min Range: -0.1526

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1430534 (Python Code)

Max Activating Token Index: 324