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

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

Neuron 4778 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6420. Min Range: -2.6420

Max Act: 2.6420. Min Act: -0.0000

Data Index: 887614 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 2.6420. Min Range: -2.6420

Max Act: 2.1762. Min Act: -0.0000

Data Index: 1025795 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 2.6420. Min Range: -2.6420

Max Act: 2.2769. Min Act: -0.0000

Data Index: 86781 (C4 (Web Text))

Max Activating Token Index: 818

Text #3

Max Range: 2.6420. Min Range: -2.6420

Max Act: 2.1916. Min Act: -0.0000

Data Index: 422543 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 2.6420. Min Range: -2.6420

Max Act: 2.1119. Min Act: -0.0000

Data Index: 852620 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 2.6420. Min Range: -2.6420

Max Act: 2.1001. Min Act: -0.0000

Data Index: 935801 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.6420. Min Range: -2.6420

Max Act: 2.0574. Min Act: -0.0000

Data Index: 767594 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.9543. Min Act: -0.0000

Data Index: 888750 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.9183. Min Act: -0.0000

Data Index: 166252 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.7409. Min Act: -0.0000

Data Index: 532628 (C4 (Web Text))

Max Activating Token Index: 867

Text #10

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.6680. Min Act: -0.0000

Data Index: 125773 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.7415. Min Act: -0.0000

Data Index: 229154 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.6439. Min Act: -0.0000

Data Index: 817852 (C4 (Web Text))

Max Activating Token Index: 576

Text #13

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.6009. Min Act: -0.0000

Data Index: 1114470 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.6057. Min Act: -0.0000

Data Index: 1034718 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.6396. Min Act: -0.0000

Data Index: 977397 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.6388. Min Act: -0.0000

Data Index: 229094 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1162341 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1158921 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 2.6420. Min Range: -2.6420

Max Act: 1.5108. Min Act: -0.0000

Data Index: 928130 (C4 (Web Text))

Max Activating Token Index: 921