Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4191 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.1300. Min Range: -5.1300

Max Act: 5.1300. Min Act: -0.0001

Data Index: 947747 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.7806. Min Act: -0.0001

Data Index: 1067821 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.9911. Min Act: -0.0001

Data Index: 1332121 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 5.1300. Min Range: -5.1300

Max Act: 5.0659. Min Act: -0.0001

Data Index: 1272597 (C4 (Web Text))

Max Activating Token Index: 427

Text #4

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.9834. Min Act: -0.0001

Data Index: 586737 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.6035. Min Act: -0.0001

Data Index: 1332925 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.5996. Min Act: -0.0001

Data Index: 245536 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.2800. Min Act: -0.0001

Data Index: 9243 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.3869. Min Act: -0.0001

Data Index: 360784 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.4756. Min Act: -0.0001

Data Index: 182789 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.3813. Min Act: -0.0001

Data Index: 878080 (C4 (Web Text))

Max Activating Token Index: 952

Text #11

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.1803. Min Act: -0.0001

Data Index: 1062059 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.3757. Min Act: -0.0001

Data Index: 472674 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.1290. Min Act: -0.0001

Data Index: 637840 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.1813. Min Act: -0.0001

Data Index: 816296 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.0631. Min Act: -0.0001

Data Index: 456745 (C4 (Web Text))

Max Activating Token Index: 358

Text #16

Max Range: 5.1300. Min Range: -5.1300

Max Act: 3.9699. Min Act: -0.0001

Data Index: 348667 (C4 (Web Text))

Max Activating Token Index: 323

Text #17

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.0024. Min Act: -0.0001

Data Index: 158399 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.2794. Min Act: -0.0001

Data Index: 166768 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 5.1300. Min Range: -5.1300

Max Act: 4.0679. Min Act: -0.0001

Data Index: 383491 (C4 (Web Text))

Max Activating Token Index: 560