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

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

Neuron 2752 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9805. Min Act: -0.0000

Data Index: 926857 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9907. Min Act: -0.0000

Data Index: 279782 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1028911 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9866. Min Act: -0.0000

Data Index: 646306 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9413. Min Act: -0.0000

Data Index: 1052756 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9287. Min Act: -0.0000

Data Index: 1026630 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9182. Min Act: -0.0000

Data Index: 908098 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8977. Min Act: -0.0000

Data Index: 671810 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.9560. Min Act: -0.0000

Data Index: 381929 (C4 (Web Text))

Max Activating Token Index: 482

Text #9

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8580. Min Act: -0.0000

Data Index: 1039904 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8304. Min Act: -0.0000

Data Index: 245098 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8936. Min Act: -0.0000

Data Index: 47929 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8418. Min Act: -0.0000

Data Index: 339522 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8898. Min Act: -0.0000

Data Index: 655964 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7949. Min Act: -0.0000

Data Index: 695621 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8388. Min Act: -0.0001

Data Index: 101656 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8680. Min Act: -0.0000

Data Index: 819193 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.7901. Min Act: -0.0000

Data Index: 990191 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8032. Min Act: -0.0000

Data Index: 812892 (C4 (Web Text))

Max Activating Token Index: 874

Text #19

Max Range: 0.9907. Min Range: -0.9907

Max Act: 0.8457. Min Act: -0.0000

Data Index: 377853 (C4 (Web Text))

Max Activating Token Index: 123