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

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

Neuron 2628 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1275242 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.5741. Min Act: -0.0001

Data Index: 862311 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1182840 (C4 (Web Text))

Max Activating Token Index: 826

Text #3

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.5280. Min Act: -0.0000

Data Index: 847102 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.5441. Min Act: -0.0000

Data Index: 393379 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4682. Min Act: -0.0000

Data Index: 579142 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4834. Min Act: -0.0000

Data Index: 490132 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.5021. Min Act: -0.0000

Data Index: 767847 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.5123. Min Act: -0.0000

Data Index: 585256 (C4 (Web Text))

Max Activating Token Index: 697

Text #9

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1358802 (C4 (Web Text))

Max Activating Token Index: 590

Text #10

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1132922 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4684. Min Act: -0.0001

Data Index: 280242 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4907. Min Act: -0.0000

Data Index: 544698 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4729. Min Act: -0.0000

Data Index: 263762 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4441. Min Act: -0.0000

Data Index: 747095 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4731. Min Act: -0.0000

Data Index: 917463 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4247. Min Act: -0.0000

Data Index: 721665 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1014937 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4522. Min Act: -0.0000

Data Index: 524559 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.9092. Min Range: -0.9092

Max Act: 0.4472. Min Act: -0.0000

Data Index: 420758 (C4 (Web Text))

Max Activating Token Index: 712