Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 990 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1289385 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2357. Min Act: -0.0000

Data Index: 231505 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2041. Min Act: -0.0001

Data Index: 730606 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1294091 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1902. Min Act: -0.0000

Data Index: 794958 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1185837 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2044. Min Act: -0.0000

Data Index: 580291 (C4 (Web Text))

Max Activating Token Index: 269

Text #7

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2076. Min Act: -0.0001

Data Index: 191984 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1172566 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.2056. Min Act: -0.0000

Data Index: 1029102 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1958. Min Act: -0.0000

Data Index: 1329563 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1199749 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1815. Min Act: -0.0001

Data Index: 865013 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1884. Min Act: -0.0000

Data Index: 559880 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1934. Min Act: -0.0000

Data Index: 528023 (C4 (Web Text))

Max Activating Token Index: 897

Text #15

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1923. Min Act: -0.0001

Data Index: 132188 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1838. Min Act: -0.0000

Data Index: 940566 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1215948 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1688. Min Act: -0.0000

Data Index: 1098704 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.2618. Min Range: -0.2618

Max Act: 0.1801. Min Act: -0.0000

Data Index: 329004 (C4 (Web Text))

Max Activating Token Index: 519