Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4164 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6935. Min Act: -0.0002

Data Index: 1408142 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.6360. Min Act: -0.0002

Data Index: 1395212 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5737. Min Act: -0.0002

Data Index: 1550028 (Python Code)

Max Activating Token Index: 19

Text #3

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4939. Min Act: -0.0002

Data Index: 1642600 (Python Code)

Max Activating Token Index: 38

Text #4

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5050. Min Act: -0.0002

Data Index: 1565676 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5105. Min Act: -0.0002

Data Index: 1554883 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5535. Min Act: -0.0002

Data Index: 1501749 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4817. Min Act: -0.0002

Data Index: 1442179 (Python Code)

Max Activating Token Index: 460

Text #8

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4805. Min Act: -0.0002

Data Index: 1645385 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.5070. Min Act: -0.0002

Data Index: 1378219 (Python Code)

Max Activating Token Index: 230

Text #10

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4998. Min Act: -0.0002

Data Index: 1386810 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4654. Min Act: -0.0002

Data Index: 1435543 (Python Code)

Max Activating Token Index: 567

Text #12

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4724. Min Act: -0.0002

Data Index: 1431006 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4691. Min Act: -0.0002

Data Index: 1373588 (Python Code)

Max Activating Token Index: 18

Text #14

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4108. Min Act: -0.0002

Data Index: 1554288 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4942. Min Act: -0.0002

Data Index: 1503450 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4816. Min Act: -0.0002

Data Index: 1635585 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4490. Min Act: -0.0002

Data Index: 1380614 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4730. Min Act: -0.0002

Data Index: 1564316 (Python Code)

Max Activating Token Index: 45

Text #19

Max Range: 0.6935. Min Range: -0.6935

Max Act: 0.4446. Min Act: -0.0002

Data Index: 1399210 (Python Code)

Max Activating Token Index: 31