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

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

Neuron 933 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: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0006

Data Index: 1186733 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0005

Data Index: 813589 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0006

Data Index: 647144 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0006

Data Index: 831733 (C4 (Web Text))

Max Activating Token Index: 959

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0006

Data Index: 854149 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0100. Min Act: -0.0006

Data Index: 496633 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0006

Data Index: 105056 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0094. Min Act: -0.0006

Data Index: 1281463 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1275694 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0006

Data Index: 216621 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0006

Data Index: 1046461 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0099. Min Act: -0.0006

Data Index: 1146998 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0006

Data Index: 480463 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0096. Min Act: -0.0006

Data Index: 162272 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 572464 (C4 (Web Text))

Max Activating Token Index: 941

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 631446 (C4 (Web Text))

Max Activating Token Index: 337

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1013316 (C4 (Web Text))

Max Activating Token Index: 395

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 810734 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1303376 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0095. Min Act: -0.0006

Data Index: 534067 (C4 (Web Text))

Max Activating Token Index: 980