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

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

Neuron 2688 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.6834. Min Act: -0.0000

Data Index: 691333 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5631. Min Act: -0.0000

Data Index: 160518 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5108. Min Act: -0.0000

Data Index: 461416 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1274185 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5104. Min Act: -0.0000

Data Index: 372606 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.5003. Min Act: -0.0000

Data Index: 709231 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1006683 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1093285 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4739. Min Act: -0.0000

Data Index: 591950 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4464. Min Act: -0.0000

Data Index: 199206 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4845. Min Act: -0.0000

Data Index: 663144 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1240090 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1126766 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4484. Min Act: -0.0000

Data Index: 703614 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4593. Min Act: -0.0000

Data Index: 643591 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4619. Min Act: -0.0000

Data Index: 1343851 (C4 (Web Text))

Max Activating Token Index: 651

Text #16

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4419. Min Act: -0.0000

Data Index: 81314 (C4 (Web Text))

Max Activating Token Index: 319

Text #17

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1088106 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4709. Min Act: -0.0000

Data Index: 451950 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.6834. Min Range: -0.6834

Max Act: 0.4216. Min Act: -0.0000

Data Index: 441779 (C4 (Web Text))

Max Activating Token Index: 667