Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2502 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.1904. Min Act: -0.0000

Data Index: 475172 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.4756. Min Act: -0.0000

Data Index: 508797 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.3443. Min Act: -0.0000

Data Index: 830361 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.4153. Min Act: -0.0000

Data Index: 60219 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.1527. Min Act: -0.0000

Data Index: 236808 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.1562. Min Act: -0.0000

Data Index: 934523 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.0392. Min Act: -0.0000

Data Index: 882914 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9466. Min Act: -0.0000

Data Index: 1305181 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.0148. Min Act: -0.0000

Data Index: 426401 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9938. Min Act: -0.0000

Data Index: 387377 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9714. Min Act: -0.0000

Data Index: 785208 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9541. Min Act: -0.0000

Data Index: 1152430 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.7776. Min Act: -0.0000

Data Index: 1246647 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9495. Min Act: -0.0000

Data Index: 1141175 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9394. Min Act: -0.0000

Data Index: 106604 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.1139. Min Act: -0.0000

Data Index: 724928 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9414. Min Act: -0.0000

Data Index: 661046 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.8495. Min Act: -0.0000

Data Index: 1200807 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.8213. Min Act: -0.0000

Data Index: 1080770 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 3.1904. Min Range: -3.1904

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1183526 (C4 (Web Text))

Max Activating Token Index: 272