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

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

Neuron 3775 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: 1.2667. Min Range: -1.2667

Max Act: 1.2667. Min Act: -0.0002

Data Index: 1583260 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1505. Min Act: -0.0002

Data Index: 1608150 (Python Code)

Max Activating Token Index: 66

Text #2

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1547. Min Act: -0.0002

Data Index: 1636837 (Python Code)

Max Activating Token Index: 58

Text #3

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1572. Min Act: -0.0002

Data Index: 1541494 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1089. Min Act: -0.0002

Data Index: 1369627 (Python Code)

Max Activating Token Index: 821

Text #5

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.1175. Min Act: -0.0002

Data Index: 1414410 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0928. Min Act: -0.0002

Data Index: 1599978 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0835. Min Act: -0.0002

Data Index: 1395640 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0809. Min Act: -0.0002

Data Index: 1398771 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0649. Min Act: -0.0002

Data Index: 1640137 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0357. Min Act: -0.0002

Data Index: 1642066 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0722. Min Act: -0.0002

Data Index: 1606688 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0242. Min Act: -0.0002

Data Index: 1614945 (Python Code)

Max Activating Token Index: 86

Text #13

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0619. Min Act: -0.0002

Data Index: 1505391 (Python Code)

Max Activating Token Index: 30

Text #14

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0336. Min Act: -0.0002

Data Index: 1573509 (Python Code)

Max Activating Token Index: 171

Text #15

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0425. Min Act: -0.0002

Data Index: 1487102 (Python Code)

Max Activating Token Index: 797

Text #16

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0288. Min Act: -0.0002

Data Index: 1518231 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0330. Min Act: -0.0002

Data Index: 1409966 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0041. Min Act: -0.0002

Data Index: 1577304 (Python Code)

Max Activating Token Index: 65

Text #19

Max Range: 1.2667. Min Range: -1.2667

Max Act: 1.0040. Min Act: -0.0002

Data Index: 1422654 (Python Code)

Max Activating Token Index: 144