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

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

Neuron 3481 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1359961 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360327 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360159 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1361211 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360022 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1361217 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360652 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1359936 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1361302 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360101 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360117 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1361175 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1361146 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360590 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1360871 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1361275 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360852 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360737 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1360494 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0356. Min Range: -0.0356

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1361259 (Python Code)

Max Activating Token Index: 1