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

Dataset: The Pile

Neuron 3075 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5818. Min Act: -0.0000

Data Index: 1540534 (The Pile)

Max Activating Token Index: 206

Text #1

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1074623 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1267619 (The Pile)

Max Activating Token Index: 359

Text #3

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1354943 (The Pile)

Max Activating Token Index: 40

Text #4

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4812. Min Act: -0.0000

Data Index: 1157815 (The Pile)

Max Activating Token Index: 617

Text #5

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1259022 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1517015 (The Pile)

Max Activating Token Index: 184

Text #7

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1748247 (The Pile)

Max Activating Token Index: 449

Text #8

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1192811 (The Pile)

Max Activating Token Index: 767

Text #9

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5456. Min Act: -0.0000

Data Index: 300736 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4709. Min Act: -0.0000

Data Index: 610385 (The Pile)

Max Activating Token Index: 862

Text #11

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4756. Min Act: -0.0000

Data Index: 669822 (The Pile)

Max Activating Token Index: 313

Text #12

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1209019 (The Pile)

Max Activating Token Index: 47

Text #13

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1456803 (The Pile)

Max Activating Token Index: 921

Text #14

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3753. Min Act: -0.0000

Data Index: 462643 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1477728 (The Pile)

Max Activating Token Index: 947

Text #16

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4440. Min Act: -0.0000

Data Index: 117533 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1431409 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4134. Min Act: -0.0000

Data Index: 957598 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 0.5818. Min Range: -0.5818

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1049273 (The Pile)

Max Activating Token Index: 616