Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 874 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0049. Min Act: -0.0005

Data Index: 973924 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0049. Min Act: -0.0006

Data Index: 1154988 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0047. Min Act: -0.0006

Data Index: 650729 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0047. Min Act: -0.0006

Data Index: 662421 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0047. Min Act: -0.0006

Data Index: 1297458 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0006

Data Index: 730961 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0047. Min Act: -0.0006

Data Index: 817395 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0006

Data Index: 927494 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0046. Min Act: -0.0006

Data Index: 1324882 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 468870 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1022379 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 351635 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 512477 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1021086 (C4 (Web Text))

Max Activating Token Index: 569

Text #14

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 937652 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 363353 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 326039 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0045. Min Act: -0.0006

Data Index: 1218087 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0006

Data Index: 605694 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.0049. Min Range: -0.0049

Max Act: 0.0044. Min Act: -0.0005

Data Index: 1143322 (C4 (Web Text))

Max Activating Token Index: 983