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

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

Neuron 4138 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.9334. Min Act: -0.0000

Data Index: 118914 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.4470. Min Act: -0.0000

Data Index: 702255 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.2902. Min Act: -0.0000

Data Index: 1041908 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.4046. Min Act: -0.0000

Data Index: 1045941 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.7120. Min Act: -0.0000

Data Index: 926620 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.3143. Min Act: -0.0000

Data Index: 804678 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.5588. Min Act: -0.0000

Data Index: 1553673 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.8304. Min Act: -0.0001

Data Index: 885839 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.0794. Min Act: -0.0000

Data Index: 860244 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.7640. Min Act: -0.0000

Data Index: 967041 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.7757. Min Act: -0.0000

Data Index: 191709 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.9078. Min Act: -0.0000

Data Index: 1271729 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 3.9334. Min Range: -3.9334

Max Act: 3.0704. Min Act: -0.0000

Data Index: 1063951 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.7612. Min Act: -0.0000

Data Index: 774932 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.8747. Min Act: -0.0000

Data Index: 568539 (C4 (Web Text))

Max Activating Token Index: 151

Text #15

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.8774. Min Act: -0.0000

Data Index: 381988 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.8942. Min Act: -0.0000

Data Index: 735073 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.8559. Min Act: -0.0000

Data Index: 706988 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.8056. Min Act: -0.0000

Data Index: 1011205 (C4 (Web Text))

Max Activating Token Index: 456

Text #19

Max Range: 3.9334. Min Range: -3.9334

Max Act: 2.5250. Min Act: -0.0000

Data Index: 1173761 (C4 (Web Text))

Max Activating Token Index: 853