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

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

Neuron 94 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: 3.2867. Min Range: -3.2867

Max Act: 3.2867. Min Act: -0.0000

Data Index: 259416 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.8108. Min Act: -0.0000

Data Index: 569158 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.7037. Min Act: -0.0000

Data Index: 226510 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.6537. Min Act: -0.0000

Data Index: 1154429 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.5996. Min Act: -0.0000

Data Index: 790994 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.5201. Min Act: -0.0000

Data Index: 1241883 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.5366. Min Act: -0.0000

Data Index: 373930 (C4 (Web Text))

Max Activating Token Index: 245

Text #7

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.4789. Min Act: -0.0000

Data Index: 906338 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.6017. Min Act: -0.0000

Data Index: 77914 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.4696. Min Act: -0.0000

Data Index: 511711 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.3382. Min Act: -0.0000

Data Index: 525492 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.3200. Min Act: -0.0000

Data Index: 1341322 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.4420. Min Act: -0.0000

Data Index: 1057495 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.4114. Min Act: -0.0000

Data Index: 783140 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.3987. Min Act: -0.0000

Data Index: 804651 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.4933. Min Act: -0.0000

Data Index: 925881 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.4737. Min Act: -0.0000

Data Index: 529954 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.4708. Min Act: -0.0000

Data Index: 359748 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.3243. Min Act: -0.0000

Data Index: 1166117 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 3.2867. Min Range: -3.2867

Max Act: 2.3231. Min Act: -0.0000

Data Index: 55448 (C4 (Web Text))

Max Activating Token Index: 653