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

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

Neuron 322 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: 3.3078. Min Range: -3.3078

Max Act: 3.3078. Min Act: -0.0002

Data Index: 1514399 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.7013. Min Act: -0.0002

Data Index: 1622289 (Python Code)

Max Activating Token Index: 996

Text #2

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.8659. Min Act: -0.0002

Data Index: 1487959 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.6651. Min Act: -0.0002

Data Index: 1553398 (Python Code)

Max Activating Token Index: 141

Text #4

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.6615. Min Act: -0.0002

Data Index: 1432906 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.4574. Min Act: -0.0002

Data Index: 1601746 (Python Code)

Max Activating Token Index: 478

Text #6

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.8683. Min Act: -0.0002

Data Index: 1653789 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.4254. Min Act: -0.0002

Data Index: 1474875 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.6622. Min Act: -0.0002

Data Index: 1392127 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.2719. Min Act: -0.0002

Data Index: 1625433 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.3956. Min Act: -0.0002

Data Index: 1585821 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.4426. Min Act: -0.0002

Data Index: 1618269 (Python Code)

Max Activating Token Index: 195

Text #12

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.6071. Min Act: -0.0002

Data Index: 1384591 (Python Code)

Max Activating Token Index: 194

Text #13

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.6728. Min Act: -0.0002

Data Index: 1363961 (Python Code)

Max Activating Token Index: 375

Text #14

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.1862. Min Act: -0.0002

Data Index: 1472924 (Python Code)

Max Activating Token Index: 728

Text #15

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.4517. Min Act: -0.0002

Data Index: 1607940 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.4475. Min Act: -0.0002

Data Index: 1573617 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.0748. Min Act: -0.0002

Data Index: 1573524 (Python Code)

Max Activating Token Index: 640

Text #18

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.5170. Min Act: -0.0002

Data Index: 1554052 (Python Code)

Max Activating Token Index: 159

Text #19

Max Range: 3.3078. Min Range: -3.3078

Max Act: 2.4874. Min Act: -0.0002

Data Index: 1559082 (Python Code)

Max Activating Token Index: 505