Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2362 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0765. Min Range: -1.0765

Max Act: 1.0765. Min Act: -0.0001

Data Index: 903010 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.8423. Min Act: -0.0000

Data Index: 1114676 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7942. Min Act: -0.0001

Data Index: 1046124 (C4 (Web Text))

Max Activating Token Index: 531

Text #3

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7644. Min Act: -0.0000

Data Index: 335960 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7258. Min Act: -0.0000

Data Index: 1174772 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7653. Min Act: -0.0001

Data Index: 1278501 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7090. Min Act: -0.0000

Data Index: 581560 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7731. Min Act: -0.0000

Data Index: 383776 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6963. Min Act: -0.0000

Data Index: 282886 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6617. Min Act: -0.0001

Data Index: 1359715 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6627. Min Act: -0.0000

Data Index: 309269 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1064781 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6774. Min Act: -0.0000

Data Index: 3124 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.7065. Min Act: -0.0000

Data Index: 426684 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1064025 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6711. Min Act: -0.0000

Data Index: 32089 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6363. Min Act: -0.0000

Data Index: 1291754 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6573. Min Act: -0.0000

Data Index: 773485 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6144. Min Act: -0.0000

Data Index: 204936 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 1.0765. Min Range: -1.0765

Max Act: 0.6090. Min Act: -0.0001

Data Index: 1240310 (C4 (Web Text))

Max Activating Token Index: 537