Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3933 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.9216. Min Act: -0.0001

Data Index: 437545 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8944. Min Act: -0.0001

Data Index: 659772 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8859. Min Act: -0.0001

Data Index: 1321254 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.8038. Min Act: -0.0001

Data Index: 1251520 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7679. Min Act: -0.0001

Data Index: 756528 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1039596 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7202. Min Act: -0.0001

Data Index: 1239869 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7427. Min Act: -0.0001

Data Index: 860469 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7644. Min Act: -0.0001

Data Index: 773197 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7395. Min Act: -0.0001

Data Index: 989431 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7587. Min Act: -0.0001

Data Index: 832997 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7593. Min Act: -0.0001

Data Index: 1325033 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7606. Min Act: -0.0001

Data Index: 87421 (C4 (Web Text))

Max Activating Token Index: 10

Text #13

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7544. Min Act: -0.0001

Data Index: 485205 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7309. Min Act: -0.0001

Data Index: 179623 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7321. Min Act: -0.0001

Data Index: 255417 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7501. Min Act: -0.0001

Data Index: 770734 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7767. Min Act: -0.0001

Data Index: 433582 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7094. Min Act: -0.0001

Data Index: 844061 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.9216. Min Range: -0.9216

Max Act: 0.7456. Min Act: -0.0001

Data Index: 823313 (C4 (Web Text))

Max Activating Token Index: 1017