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

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

Neuron 3793 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0002

Data Index: 323500 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0544. Min Act: -0.0003

Data Index: 472386 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0520. Min Act: -0.0003

Data Index: 886868 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1079821 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0487. Min Act: -0.0002

Data Index: 943770 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0505. Min Act: -0.0002

Data Index: 345622 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0484. Min Act: -0.0003

Data Index: 918317 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0485. Min Act: -0.0003

Data Index: 525890 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0492. Min Act: -0.0003

Data Index: 1116997 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0485. Min Act: -0.0003

Data Index: 301569 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0449. Min Act: -0.0003

Data Index: 1106519 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0476. Min Act: -0.0003

Data Index: 842538 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0460. Min Act: -0.0003

Data Index: 901953 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0463. Min Act: -0.0002

Data Index: 808532 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0423. Min Act: -0.0003

Data Index: 975144 (C4 (Web Text))

Max Activating Token Index: 523

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0437. Min Act: -0.0003

Data Index: 371545 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0433. Min Act: -0.0003

Data Index: 310026 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0417. Min Act: -0.0003

Data Index: 714251 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1022943 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0444. Min Act: -0.0003

Data Index: 137935 (C4 (Web Text))

Max Activating Token Index: 797