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

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

Neuron 3940 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: 2.3729. Min Range: -2.3729

Max Act: 2.3729. Min Act: -0.0000

Data Index: 34656 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.2247. Min Act: -0.0000

Data Index: 998001 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.2530. Min Act: -0.0000

Data Index: 1206130 (C4 (Web Text))

Max Activating Token Index: 925

Text #3

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.9750. Min Act: -0.0000

Data Index: 521764 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.0797. Min Act: -0.0000

Data Index: 1055561 (C4 (Web Text))

Max Activating Token Index: 707

Text #5

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.1910. Min Act: -0.0000

Data Index: 11193 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.0364. Min Act: -0.0000

Data Index: 981372 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.1375. Min Act: -0.0000

Data Index: 62728 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.2112. Min Act: -0.0000

Data Index: 200241 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.1384. Min Act: -0.0000

Data Index: 921258 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.9524. Min Act: -0.0000

Data Index: 721901 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.9051. Min Act: -0.0000

Data Index: 1212842 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.7348. Min Act: -0.0000

Data Index: 791114 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 2.3729. Min Range: -2.3729

Max Act: 2.0035. Min Act: -0.0000

Data Index: 815566 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.9544. Min Act: -0.0000

Data Index: 891702 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.7390. Min Act: -0.0000

Data Index: 1220752 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.9454. Min Act: -0.0000

Data Index: 126036 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.8778. Min Act: -0.0000

Data Index: 360119 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.9909. Min Act: -0.0000

Data Index: 195590 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 2.3729. Min Range: -2.3729

Max Act: 1.8802. Min Act: -0.0000

Data Index: 501036 (C4 (Web Text))

Max Activating Token Index: 96