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

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

Neuron 1725 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0996. Min Range: -1.0996

Max Act: 1.0996. Min Act: -0.0001

Data Index: 787899 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 1.0996. Min Range: -1.0996

Max Act: 1.0418. Min Act: -0.0001

Data Index: 899911 (C4 (Web Text))

Max Activating Token Index: 869

Text #2

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9849. Min Act: -0.0001

Data Index: 1514523 (Python Code)

Max Activating Token Index: 614

Text #3

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8671. Min Act: -0.0001

Data Index: 572095 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.7976. Min Act: -0.0001

Data Index: 500206 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8280. Min Act: -0.0001

Data Index: 302038 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.9108. Min Act: -0.0001

Data Index: 521747 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8829. Min Act: -0.0001

Data Index: 538089 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8265. Min Act: -0.0001

Data Index: 646475 (C4 (Web Text))

Max Activating Token Index: 633

Text #9

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8306. Min Act: -0.0001

Data Index: 275916 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8249. Min Act: -0.0001

Data Index: 902509 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.7932. Min Act: -0.0001

Data Index: 651123 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8168. Min Act: -0.0001

Data Index: 849479 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8065. Min Act: -0.0001

Data Index: 1065570 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.7774. Min Act: -0.0001

Data Index: 239222 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.7766. Min Act: -0.0001

Data Index: 745559 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.7666. Min Act: -0.0001

Data Index: 391381 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.6375. Min Act: -0.0001

Data Index: 876866 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.7413. Min Act: -0.0001

Data Index: 671750 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 1.0996. Min Range: -1.0996

Max Act: 0.8830. Min Act: -0.0001

Data Index: 1253196 (C4 (Web Text))

Max Activating Token Index: 604