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

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

Neuron 3235 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1751. Min Range: -2.1751

Max Act: 2.1751. Min Act: -0.0000

Data Index: 1274885 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 2.1751. Min Range: -2.1751

Max Act: 2.0187. Min Act: -0.0000

Data Index: 625440 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.9081. Min Act: -0.0000

Data Index: 1471799 (Python Code)

Max Activating Token Index: 574

Text #3

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.9086. Min Act: -0.0000

Data Index: 61649 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.9020. Min Act: -0.0000

Data Index: 1488056 (Python Code)

Max Activating Token Index: 628

Text #5

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7961. Min Act: -0.0000

Data Index: 160975 (C4 (Web Text))

Max Activating Token Index: 948

Text #6

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.8558. Min Act: -0.0000

Data Index: 287622 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7410. Min Act: -0.0000

Data Index: 1356381 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7950. Min Act: -0.0000

Data Index: 1371687 (Python Code)

Max Activating Token Index: 774

Text #9

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1038790 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7734. Min Act: -0.0000

Data Index: 1508125 (Python Code)

Max Activating Token Index: 670

Text #11

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7852. Min Act: -0.0000

Data Index: 652886 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7178. Min Act: -0.0000

Data Index: 964269 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7697. Min Act: -0.0000

Data Index: 577996 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7000. Min Act: -0.0001

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7510. Min Act: -0.0000

Data Index: 1189494 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7104. Min Act: -0.0000

Data Index: 591461 (C4 (Web Text))

Max Activating Token Index: 498

Text #17

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7232. Min Act: -0.0000

Data Index: 265035 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1191463 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 2.1751. Min Range: -2.1751

Max Act: 1.6508. Min Act: -0.0000

Data Index: 369020 (C4 (Web Text))

Max Activating Token Index: 895