Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1420 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.9199. Min Act: 0.0000

Data Index: 691614 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.0137. Min Range: -3.0137

Max Act: 3.0137. Min Act: 0.0001

Data Index: 257059 (C4 (Web Text))

Max Activating Token Index: 207

Text #2

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.6622. Min Act: 0.0000

Data Index: 821559 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.6161. Min Act: -0.0000

Data Index: 636715 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.4379. Min Act: -0.0000

Data Index: 1011286 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.4390. Min Act: 0.0000

Data Index: 1156921 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.6843. Min Act: -0.0000

Data Index: 52564 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.3905. Min Act: 0.0000

Data Index: 288402 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.3878. Min Act: -0.0000

Data Index: 1113648 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.4687. Min Act: -0.0000

Data Index: 480522 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.3416. Min Act: 0.0001

Data Index: 888586 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.9476. Min Act: -0.0000

Data Index: 122223 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.5643. Min Act: -0.0000

Data Index: 886073 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.1161. Min Act: 0.0000

Data Index: 932419 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.3203. Min Act: -0.0000

Data Index: 1115555 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.3263. Min Act: 0.0000

Data Index: 813962 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.2960. Min Act: -0.0000

Data Index: 889732 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.3208. Min Act: 0.0000

Data Index: 1082593 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.1521. Min Act: -0.0000

Data Index: 638993 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 3.0137. Min Range: -3.0137

Max Act: 2.0375. Min Act: 0.0001

Data Index: 625443 (C4 (Web Text))

Max Activating Token Index: 702