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

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

Neuron 1964 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: 2.1153. Min Range: -2.1153

Max Act: 2.1153. Min Act: -0.0000

Data Index: 765027 (C4 (Web Text))

Max Activating Token Index: 96

Text #1

Max Range: 2.1153. Min Range: -2.1153

Max Act: 2.0367. Min Act: -0.0000

Data Index: 240895 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.8815. Min Act: -0.0000

Data Index: 17766 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 2.1153. Min Range: -2.1153

Max Act: 2.0542. Min Act: -0.0000

Data Index: 23261 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.9442. Min Act: -0.0000

Data Index: 189281 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.8157. Min Act: -0.0000

Data Index: 693964 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.7366. Min Act: -0.0000

Data Index: 1296292 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.6760. Min Act: -0.0000

Data Index: 970687 (C4 (Web Text))

Max Activating Token Index: 166

Text #8

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5222. Min Act: -0.0000

Data Index: 1014827 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.7006. Min Act: -0.0000

Data Index: 975328 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.6137. Min Act: -0.0000

Data Index: 221642 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5345. Min Act: -0.0000

Data Index: 363517 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.6455. Min Act: -0.0000

Data Index: 385606 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5815. Min Act: -0.0000

Data Index: 802506 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5816. Min Act: -0.0000

Data Index: 760225 (C4 (Web Text))

Max Activating Token Index: 314

Text #15

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5616. Min Act: -0.0000

Data Index: 57685 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5877. Min Act: -0.0000

Data Index: 362635 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.4619. Min Act: -0.0000

Data Index: 818543 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5414. Min Act: -0.0000

Data Index: 835919 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 2.1153. Min Range: -2.1153

Max Act: 1.5121. Min Act: -0.0000

Data Index: 1350080 (C4 (Web Text))

Max Activating Token Index: 193