Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1330 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5879. Min Act: -0.0006

Data Index: 1404121 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5866. Min Act: -0.0005

Data Index: 1567872 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5879. Min Act: -0.0005

Data Index: 1647722 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5338. Min Act: -0.0005

Data Index: 1560076 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5148. Min Act: -0.0005

Data Index: 1565153 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5186. Min Act: -0.0005

Data Index: 1547512 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5305. Min Act: -0.0005

Data Index: 1476478 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5300. Min Act: -0.0005

Data Index: 1653666 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5033. Min Act: -0.0005

Data Index: 1380808 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5146. Min Act: -0.0005

Data Index: 1368498 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4960. Min Act: -0.0005

Data Index: 1517888 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.5016. Min Act: -0.0005

Data Index: 1566922 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4825. Min Act: -0.0006

Data Index: 1506290 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4946. Min Act: -0.0005

Data Index: 1490204 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4809. Min Act: -0.0005

Data Index: 1369264 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4769. Min Act: -0.0005

Data Index: 1628446 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4698. Min Act: -0.0005

Data Index: 1551186 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4661. Min Act: -0.0006

Data Index: 1613578 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4761. Min Act: -0.0005

Data Index: 1455998 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.5879. Min Range: -0.5879

Max Act: 0.4608. Min Act: -0.0005

Data Index: 1404247 (Python Code)

Max Activating Token Index: 1023