Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 774 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.7974. Min Act: -0.0000

Data Index: 507432 (C4 (Web Text))

Max Activating Token Index: 354

Text #1

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.5622. Min Act: -0.0000

Data Index: 45350 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.7276. Min Act: -0.0000

Data Index: 446029 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.6980. Min Act: -0.0000

Data Index: 242717 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.5824. Min Act: -0.0000

Data Index: 973008 (C4 (Web Text))

Max Activating Token Index: 960

Text #5

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.4636. Min Act: -0.0000

Data Index: 994945 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.3057. Min Act: -0.0000

Data Index: 338004 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.3070. Min Act: -0.0000

Data Index: 1338709 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.1164. Min Act: -0.0000

Data Index: 138983 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.0850. Min Act: -0.0000

Data Index: 264041 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.3324. Min Act: -0.0000

Data Index: 148997 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.1581. Min Act: -0.0000

Data Index: 705837 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.0917. Min Act: -0.0000

Data Index: 358792 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.1953. Min Act: -0.0000

Data Index: 886079 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 3.7974. Min Range: -3.7974

Max Act: 2.8940. Min Act: -0.0000

Data Index: 108740 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 3.7974. Min Range: -3.7974

Max Act: 2.9987. Min Act: -0.0000

Data Index: 1291690 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 3.7974. Min Range: -3.7974

Max Act: 2.7872. Min Act: -0.0000

Data Index: 624168 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 3.7974. Min Range: -3.7974

Max Act: 3.0218. Min Act: -0.0000

Data Index: 387168 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 3.7974. Min Range: -3.7974

Max Act: 2.8488. Min Act: -0.0000

Data Index: 450861 (C4 (Web Text))

Max Activating Token Index: 303

Text #19

Max Range: 3.7974. Min Range: -3.7974

Max Act: 2.6838. Min Act: -0.0000

Data Index: 1081510 (C4 (Web Text))

Max Activating Token Index: 957