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

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

Neuron 4200 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.4896. Min Act: -0.0000

Data Index: 886044 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.0099. Min Act: -0.0000

Data Index: 972268 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.9758. Min Act: -0.0000

Data Index: 662087 (C4 (Web Text))

Max Activating Token Index: 931

Text #3

Max Range: 4.4896. Min Range: -4.4896

Max Act: 4.1159. Min Act: -0.0000

Data Index: 380877 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.7451. Min Act: -0.0000

Data Index: 939772 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.7307. Min Act: -0.0000

Data Index: 731262 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.8615. Min Act: -0.0000

Data Index: 1259500 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.5573. Min Act: -0.0000

Data Index: 334041 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.8004. Min Act: -0.0000

Data Index: 1055633 (C4 (Web Text))

Max Activating Token Index: 502

Text #9

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.6262. Min Act: -0.0000

Data Index: 810298 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.7728. Min Act: -0.0000

Data Index: 577346 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.5876. Min Act: -0.0000

Data Index: 289432 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.4444. Min Act: -0.0000

Data Index: 988570 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.5479. Min Act: -0.0000

Data Index: 1338386 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.3823. Min Act: -0.0000

Data Index: 1208391 (C4 (Web Text))

Max Activating Token Index: 222

Text #15

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.5021. Min Act: -0.0000

Data Index: 86426 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.4767. Min Act: -0.0000

Data Index: 485156 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.6203. Min Act: -0.0000

Data Index: 385442 (C4 (Web Text))

Max Activating Token Index: 418

Text #18

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.2967. Min Act: 0.0000

Data Index: 1310606 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 4.4896. Min Range: -4.4896

Max Act: 3.4529. Min Act: -0.0000

Data Index: 172163 (C4 (Web Text))

Max Activating Token Index: 639