Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3794 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0094. Min Range: -3.0094

Max Act: 3.0094. Min Act: -0.0000

Data Index: 917859 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.8457. Min Act: -0.0000

Data Index: 1222044 (C4 (Web Text))

Max Activating Token Index: 763

Text #2

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.7168. Min Act: -0.0000

Data Index: 222565 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.3371. Min Act: -0.0000

Data Index: 1649196 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.4438. Min Act: -0.0000

Data Index: 662304 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.4172. Min Act: -0.0000

Data Index: 659684 (C4 (Web Text))

Max Activating Token Index: 969

Text #6

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.5498. Min Act: -0.0000

Data Index: 170615 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.3800. Min Act: -0.0000

Data Index: 556899 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2246. Min Act: -0.0000

Data Index: 1236844 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2917. Min Act: -0.0000

Data Index: 136127 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2431. Min Act: -0.0000

Data Index: 259265 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2091. Min Act: -0.0000

Data Index: 1060672 (C4 (Web Text))

Max Activating Token Index: 704

Text #12

Max Range: 3.0094. Min Range: -3.0094

Max Act: 1.9851. Min Act: -0.0000

Data Index: 1336573 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2274. Min Act: -0.0000

Data Index: 481518 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2049. Min Act: -0.0000

Data Index: 639582 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2121. Min Act: -0.0000

Data Index: 1357991 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.2253. Min Act: -0.0000

Data Index: 1342583 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.1450. Min Act: -0.0000

Data Index: 5134 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.1691. Min Act: -0.0000

Data Index: 345284 (C4 (Web Text))

Max Activating Token Index: 350

Text #19

Max Range: 3.0094. Min Range: -3.0094

Max Act: 2.1492. Min Act: -0.0000

Data Index: 166760 (C4 (Web Text))

Max Activating Token Index: 789