Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2870 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5085. Min Act: -0.0004

Data Index: 1621859 (Python Code)

Max Activating Token Index: 530

Text #1

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5036. Min Act: -0.0004

Data Index: 1488288 (Python Code)

Max Activating Token Index: 250

Text #2

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4980. Min Act: -0.0004

Data Index: 1486877 (Python Code)

Max Activating Token Index: 183

Text #3

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4806. Min Act: -0.0004

Data Index: 1459165 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4922. Min Act: -0.0004

Data Index: 1482133 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5080. Min Act: -0.0004

Data Index: 1645445 (Python Code)

Max Activating Token Index: 485

Text #6

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5055. Min Act: -0.0004

Data Index: 1631941 (Python Code)

Max Activating Token Index: 629

Text #7

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4229. Min Act: -0.0004

Data Index: 1603928 (Python Code)

Max Activating Token Index: 835

Text #8

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4844. Min Act: -0.0004

Data Index: 1530953 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5294. Min Act: -0.0004

Data Index: 1495971 (Python Code)

Max Activating Token Index: 318

Text #10

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4748. Min Act: -0.0004

Data Index: 1595743 (Python Code)

Max Activating Token Index: 811

Text #11

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5071. Min Act: -0.0004

Data Index: 1432339 (Python Code)

Max Activating Token Index: 782

Text #12

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5062. Min Act: -0.0004

Data Index: 1470728 (Python Code)

Max Activating Token Index: 677

Text #13

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5052. Min Act: -0.0004

Data Index: 1463396 (Python Code)

Max Activating Token Index: 119

Text #14

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.5033. Min Act: -0.0004

Data Index: 1532941 (Python Code)

Max Activating Token Index: 847

Text #15

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4228. Min Act: -0.0004

Data Index: 1432712 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4976. Min Act: -0.0004

Data Index: 1533222 (Python Code)

Max Activating Token Index: 756

Text #17

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4842. Min Act: -0.0004

Data Index: 1536300 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4762. Min Act: -0.0004

Data Index: 1436441 (Python Code)

Max Activating Token Index: 624

Text #19

Max Range: 0.5294. Min Range: -0.5294

Max Act: 0.4494. Min Act: -0.0004

Data Index: 1586276 (Python Code)

Max Activating Token Index: 1001