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

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

Neuron 1546 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: 1.0003. Min Range: -1.0003

Max Act: 1.0003. Min Act: -0.0001

Data Index: 1459477 (Python Code)

Max Activating Token Index: 849

Text #1

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.9167. Min Act: -0.0001

Data Index: 1610128 (Python Code)

Max Activating Token Index: 68

Text #2

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.8241. Min Act: -0.0001

Data Index: 1634734 (Python Code)

Max Activating Token Index: 478

Text #3

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7974. Min Act: -0.0001

Data Index: 41711 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7705. Min Act: -0.0001

Data Index: 1367183 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7715. Min Act: -0.0001

Data Index: 1591735 (Python Code)

Max Activating Token Index: 372

Text #6

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7840. Min Act: -0.0001

Data Index: 605546 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6998. Min Act: -0.0001

Data Index: 563286 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7844. Min Act: -0.0001

Data Index: 1604386 (Python Code)

Max Activating Token Index: 43

Text #9

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7429. Min Act: -0.0001

Data Index: 241102 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6928. Min Act: -0.0001

Data Index: 1571361 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7840. Min Act: -0.0001

Data Index: 1407666 (Python Code)

Max Activating Token Index: 94

Text #12

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7048. Min Act: -0.0001

Data Index: 1586115 (Python Code)

Max Activating Token Index: 355

Text #13

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7413. Min Act: -0.0001

Data Index: 661650 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7492. Min Act: -0.0001

Data Index: 1420041 (Python Code)

Max Activating Token Index: 408

Text #15

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1491886 (Python Code)

Max Activating Token Index: 272

Text #16

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7052. Min Act: -0.0001

Data Index: 1637096 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.6797. Min Act: -0.0001

Data Index: 508079 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7463. Min Act: -0.0001

Data Index: 1295180 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 1.0003. Min Range: -1.0003

Max Act: 0.7701. Min Act: -0.0001

Data Index: 1035291 (C4 (Web Text))

Max Activating Token Index: 30