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

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

Neuron 4044 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1438237 (Python Code)

Max Activating Token Index: 589

Text #1

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.4569. Min Act: -0.0000

Data Index: 927727 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1124818 (C4 (Web Text))

Max Activating Token Index: 215

Text #3

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3994. Min Act: -0.0000

Data Index: 712462 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3107. Min Act: -0.0000

Data Index: 596236 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3607. Min Act: -0.0000

Data Index: 1493691 (Python Code)

Max Activating Token Index: 251

Text #6

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3038. Min Act: -0.0000

Data Index: 948957 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2444. Min Act: -0.0000

Data Index: 1266415 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3669. Min Act: -0.0000

Data Index: 678986 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1643774 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1618880 (Python Code)

Max Activating Token Index: 235

Text #11

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1796. Min Act: -0.0000

Data Index: 656385 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.2644. Min Act: -0.0000

Data Index: 225067 (C4 (Web Text))

Max Activating Token Index: 940

Text #13

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1539. Min Act: -0.0000

Data Index: 424251 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1443. Min Act: -0.0000

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1084891 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.0967. Min Act: -0.0000

Data Index: 554733 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 1.6030. Min Range: -1.6030

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1606080 (Python Code)

Max Activating Token Index: 139

Text #18

Max Range: 1.6030. Min Range: -1.6030

Max Act: 1.1222. Min Act: -0.0000

Data Index: 2867 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 1.6030. Min Range: -1.6030

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1457926 (Python Code)

Max Activating Token Index: 833