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

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

Neuron 236 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: 0.0061. Min Range: -0.0061

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1376534 (Python Code)

Max Activating Token Index: 414

Text #1

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0061. Min Act: -0.0005

Data Index: 1512529 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0061. Min Act: -0.0006

Data Index: 1469498 (Python Code)

Max Activating Token Index: 230

Text #3

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0060. Min Act: -0.0005

Data Index: 1538362 (Python Code)

Max Activating Token Index: 673

Text #4

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0059. Min Act: -0.0006

Data Index: 1561223 (Python Code)

Max Activating Token Index: 124

Text #5

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0059. Min Act: -0.0005

Data Index: 1609487 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1517394 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1518901 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1516153 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1373355 (Python Code)

Max Activating Token Index: 853

Text #10

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0058. Min Act: -0.0006

Data Index: 1370809 (Python Code)

Max Activating Token Index: 272

Text #11

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1645691 (Python Code)

Max Activating Token Index: 515

Text #12

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1523885 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1445845 (Python Code)

Max Activating Token Index: 41

Text #14

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1582822 (Python Code)

Max Activating Token Index: 1006

Text #15

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0006

Data Index: 1602598 (Python Code)

Max Activating Token Index: 515

Text #16

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1369059 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1451807 (Python Code)

Max Activating Token Index: 510

Text #18

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1547323 (Python Code)

Max Activating Token Index: 162

Text #19

Max Range: 0.0061. Min Range: -0.0061

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1581247 (Python Code)

Max Activating Token Index: 603