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

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

Neuron 4109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.3425. Min Act: -0.0001

Data Index: 1144174 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.8900. Min Act: -0.0001

Data Index: 966078 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 3.3425. Min Range: -3.3425

Max Act: 3.0554. Min Act: -0.0000

Data Index: 765934 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.8936. Min Act: -0.0001

Data Index: 172620 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.9210. Min Act: -0.0001

Data Index: 743143 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.5297. Min Act: -0.0001

Data Index: 699784 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.8065. Min Act: -0.0001

Data Index: 82810 (C4 (Web Text))

Max Activating Token Index: 839

Text #7

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.7611. Min Act: -0.0001

Data Index: 1123358 (C4 (Web Text))

Max Activating Token Index: 494

Text #8

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.8814. Min Act: -0.0000

Data Index: 917612 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.8902. Min Act: -0.0001

Data Index: 1069407 (C4 (Web Text))

Max Activating Token Index: 694

Text #10

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.8552. Min Act: -0.0001

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.7012. Min Act: -0.0001

Data Index: 753064 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.8163. Min Act: -0.0001

Data Index: 28397 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.6342. Min Act: -0.0001

Data Index: 32972 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.7890. Min Act: -0.0001

Data Index: 1158833 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.7890. Min Act: -0.0000

Data Index: 1357174 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.7890. Min Act: -0.0001

Data Index: 85046 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.5346. Min Act: -0.0001

Data Index: 630190 (C4 (Web Text))

Max Activating Token Index: 1016

Text #18

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.7871. Min Act: -0.0001

Data Index: 341104 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 3.3425. Min Range: -3.3425

Max Act: 2.5214. Min Act: -0.0001

Data Index: 6335 (C4 (Web Text))

Max Activating Token Index: 610