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

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

Neuron 2934 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: 1.4219. Min Range: -1.4219

Max Act: 1.4219. Min Act: -0.0001

Data Index: 377589 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1830. Min Act: -0.0001

Data Index: 543774 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1129. Min Act: -0.0001

Data Index: 968163 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.1908. Min Act: -0.0001

Data Index: 161679 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0651. Min Act: -0.0001

Data Index: 717705 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0347. Min Act: -0.0001

Data Index: 1203557 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0673. Min Act: -0.0001

Data Index: 280993 (C4 (Web Text))

Max Activating Token Index: 421

Text #7

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0218. Min Act: -0.0001

Data Index: 455540 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0442. Min Act: -0.0001

Data Index: 804808 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9850. Min Act: -0.0001

Data Index: 1327641 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9727. Min Act: -0.0001

Data Index: 559990 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1004134 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9702. Min Act: -0.0001

Data Index: 157372 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1081677 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.4219. Min Range: -1.4219

Max Act: 1.0183. Min Act: -0.0001

Data Index: 956542 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9839. Min Act: -0.0001

Data Index: 1083375 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9823. Min Act: -0.0001

Data Index: 343396 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9409. Min Act: -0.0001

Data Index: 585170 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9618. Min Act: -0.0001

Data Index: 1147718 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 1.4219. Min Range: -1.4219

Max Act: 0.9557. Min Act: -0.0001

Data Index: 1061861 (C4 (Web Text))

Max Activating Token Index: 372