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

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

Neuron 1881 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4492. Min Act: -0.0000

Data Index: 50146 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4016. Min Act: -0.0000

Data Index: 1170676 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.4089. Min Act: -0.0000

Data Index: 285838 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3900. Min Act: -0.0000

Data Index: 563033 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3603. Min Act: -0.0000

Data Index: 660904 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3859. Min Act: -0.0000

Data Index: 914271 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3574. Min Act: -0.0000

Data Index: 407288 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3523. Min Act: -0.0000

Data Index: 117069 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3415. Min Act: -0.0000

Data Index: 1184034 (C4 (Web Text))

Max Activating Token Index: 759

Text #9

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2847. Min Act: -0.0000

Data Index: 905267 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3334. Min Act: -0.0000

Data Index: 686178 (C4 (Web Text))

Max Activating Token Index: 887

Text #11

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3069. Min Act: -0.0000

Data Index: 611128 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.3019. Min Act: -0.0000

Data Index: 87203 (C4 (Web Text))

Max Activating Token Index: 365

Text #13

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2843. Min Act: -0.0000

Data Index: 414900 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2910. Min Act: -0.0000

Data Index: 1101481 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2921. Min Act: -0.0000

Data Index: 817076 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2851. Min Act: -0.0000

Data Index: 312733 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2932. Min Act: -0.0000

Data Index: 1040223 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2772. Min Act: -0.0000

Data Index: 905037 (C4 (Web Text))

Max Activating Token Index: 880

Text #19

Max Range: 0.4492. Min Range: -0.4492

Max Act: 0.2815. Min Act: -0.0000

Data Index: 618348 (C4 (Web Text))

Max Activating Token Index: 371