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

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

Neuron 13 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1275828 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3812. Min Act: -0.0000

Data Index: 600764 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3531. Min Act: -0.0000

Data Index: 343539 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1425502 (Python Code)

Max Activating Token Index: 441

Text #4

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3280. Min Act: -0.0000

Data Index: 96102 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3220. Min Act: -0.0000

Data Index: 964548 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2905. Min Act: -0.0000

Data Index: 268215 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3116. Min Act: -0.0000

Data Index: 1227778 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3627. Min Act: -0.0000

Data Index: 70801 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1083476 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1058636 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2950. Min Act: -0.0000

Data Index: 374676 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2794. Min Act: -0.0000

Data Index: 1258775 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3216. Min Act: -0.0000

Data Index: 749341 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1349108 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3170. Min Act: -0.0000

Data Index: 614890 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3153. Min Act: -0.0000

Data Index: 624404 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.3074. Min Act: -0.0000

Data Index: 1266635 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1051951 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.4303. Min Range: -0.4303

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1399491 (Python Code)

Max Activating Token Index: 265