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

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

Neuron 56 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.7105. Min Act: -0.0002

Data Index: 96116 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6419. Min Act: -0.0002

Data Index: 1124117 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6798. Min Act: -0.0002

Data Index: 189800 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5955. Min Act: -0.0001

Data Index: 1336813 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5955. Min Act: -0.0002

Data Index: 857421 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.6004. Min Act: -0.0002

Data Index: 487384 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5977. Min Act: -0.0001

Data Index: 1273668 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5904. Min Act: -0.0001

Data Index: 111647 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5572. Min Act: -0.0002

Data Index: 1344923 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5985. Min Act: -0.0001

Data Index: 1358969 (C4 (Web Text))

Max Activating Token Index: 935

Text #10

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5976. Min Act: -0.0002

Data Index: 1204138 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5553. Min Act: -0.0002

Data Index: 116940 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5745. Min Act: -0.0002

Data Index: 59609 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5774. Min Act: -0.0001

Data Index: 1066011 (C4 (Web Text))

Max Activating Token Index: 998

Text #14

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5742. Min Act: -0.0001

Data Index: 997675 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5538. Min Act: -0.0001

Data Index: 652649 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5336. Min Act: -0.0002

Data Index: 110423 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5642. Min Act: -0.0001

Data Index: 364913 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5565. Min Act: -0.0001

Data Index: 981204 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 0.7105. Min Range: -0.7105

Max Act: 0.5296. Min Act: -0.0001

Data Index: 581766 (C4 (Web Text))

Max Activating Token Index: 859