Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1657 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.8783. Min Act: 0.0001

Data Index: 1493231 (Python Code)

Max Activating Token Index: 118

Text #1

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7542. Min Act: -0.0000

Data Index: 1496362 (Python Code)

Max Activating Token Index: 161

Text #2

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1501205 (Python Code)

Max Activating Token Index: 559

Text #3

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6573. Min Act: -0.0001

Data Index: 1426034 (Python Code)

Max Activating Token Index: 149

Text #4

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6215. Min Act: -0.0001

Data Index: 1586436 (Python Code)

Max Activating Token Index: 441

Text #5

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5772. Min Act: 0.0001

Data Index: 1460857 (Python Code)

Max Activating Token Index: 713

Text #6

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1493599 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1462712 (Python Code)

Max Activating Token Index: 114

Text #8

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5412. Min Act: -0.0001

Data Index: 1580022 (Python Code)

Max Activating Token Index: 283

Text #9

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5337. Min Act: 0.0000

Data Index: 1547315 (Python Code)

Max Activating Token Index: 11

Text #10

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5168. Min Act: -0.0001

Data Index: 1377222 (Python Code)

Max Activating Token Index: 968

Text #11

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1422160 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5468. Min Act: -0.0001

Data Index: 1444923 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1524784 (Python Code)

Max Activating Token Index: 505

Text #14

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1453418 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.4913. Min Act: -0.0000

Data Index: 1530099 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1374370 (Python Code)

Max Activating Token Index: 490

Text #17

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.4953. Min Act: 0.0001

Data Index: 1367756 (Python Code)

Max Activating Token Index: 73

Text #18

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.4931. Min Act: -0.0001

Data Index: 1478809 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.4945. Min Act: -0.0001

Data Index: 1610474 (Python Code)

Max Activating Token Index: 289