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

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

Neuron 4721 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.4938. Min Act: -0.0000

Data Index: 214916 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1221047 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.2470. Min Act: -0.0000

Data Index: 1205234 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0918. Min Act: -0.0000

Data Index: 1253090 (C4 (Web Text))

Max Activating Token Index: 830

Text #4

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.1910. Min Act: -0.0000

Data Index: 306592 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.1010. Min Act: -0.0000

Data Index: 314573 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0652. Min Act: -0.0000

Data Index: 1283856 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1277858 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0368. Min Act: -0.0000

Data Index: 712911 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.1642. Min Act: -0.0000

Data Index: 1227615 (C4 (Web Text))

Max Activating Token Index: 696

Text #10

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.1054. Min Act: -0.0000

Data Index: 311881 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0923. Min Act: -0.0000

Data Index: 85653 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0795. Min Act: -0.0000

Data Index: 292708 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0660. Min Act: -0.0000

Data Index: 147949 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.4938. Min Range: -1.4938

Max Act: 0.9450. Min Act: -0.0000

Data Index: 79609 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1163506 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1251620 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0650. Min Act: -0.0000

Data Index: 456665 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0787. Min Act: -0.0000

Data Index: 944127 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.4938. Min Range: -1.4938

Max Act: 1.0895. Min Act: -0.0000

Data Index: 981738 (C4 (Web Text))

Max Activating Token Index: 464