Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 700 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1314901 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0049. Min Act: -0.0005

Data Index: 1243658 (C4 (Web Text))

Max Activating Token Index: 439

Text #2

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0005

Data Index: 1256426 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0046. Min Act: -0.0005

Data Index: 779783 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0045. Min Act: -0.0005

Data Index: 573267 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0044. Min Act: -0.0005

Data Index: 367887 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1097019 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1245260 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0043. Min Act: -0.0006

Data Index: 413486 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1338786 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0042. Min Act: -0.0005

Data Index: 956025 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0042. Min Act: -0.0005

Data Index: 570156 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1350973 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0041. Min Act: -0.0005

Data Index: 994186 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0042. Min Act: -0.0005

Data Index: 930248 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0041. Min Act: -0.0005

Data Index: 737716 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0041. Min Act: -0.0005

Data Index: 329140 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0041. Min Act: -0.0005

Data Index: 268051 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0041. Min Act: -0.0005

Data Index: 860497 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 0.0058. Min Range: -0.0058

Max Act: 0.0041. Min Act: -0.0005

Data Index: 1205733 (C4 (Web Text))

Max Activating Token Index: 184