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

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

Neuron 1128 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: 1.3716. Min Range: -1.3716

Max Act: 1.3653. Min Act: -0.0000

Data Index: 631583 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1428021 (Python Code)

Max Activating Token Index: 801

Text #2

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1384. Min Act: -0.0000

Data Index: 466837 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2602. Min Act: -0.0000

Data Index: 976878 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2250. Min Act: -0.0000

Data Index: 922959 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3192. Min Act: -0.0000

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1523. Min Act: -0.0000

Data Index: 83279 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1059. Min Act: -0.0000

Data Index: 166032 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0146. Min Act: -0.0000

Data Index: 312495 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0851. Min Act: -0.0000

Data Index: 768034 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0245. Min Act: -0.0000

Data Index: 886688 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9510. Min Act: -0.0000

Data Index: 421491 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9741. Min Act: -0.0000

Data Index: 876901 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0214. Min Act: -0.0000

Data Index: 308030 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9685. Min Act: -0.0000

Data Index: 740384 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9889. Min Act: -0.0000

Data Index: 921846 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.0279. Min Act: -0.0000

Data Index: 752057 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1134284 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1133661 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9962. Min Act: -0.0000

Data Index: 3040 (C4 (Web Text))

Max Activating Token Index: 40