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

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

Neuron 2942 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: 3.0370. Min Range: -3.0370

Max Act: 3.0370. Min Act: -0.0000

Data Index: 877354 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.1469. Min Act: -0.0000

Data Index: 624984 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.0843. Min Act: -0.0000

Data Index: 187800 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.9029. Min Act: -0.0000

Data Index: 901275 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.9950. Min Act: -0.0000

Data Index: 281391 (C4 (Web Text))

Max Activating Token Index: 330

Text #5

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.9581. Min Act: -0.0000

Data Index: 1262872 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.9095. Min Act: -0.0000

Data Index: 324516 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.0611. Min Act: 0.0000

Data Index: 1571681 (Python Code)

Max Activating Token Index: 397

Text #8

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.9286. Min Act: -0.0000

Data Index: 959280 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.8097. Min Act: -0.0000

Data Index: 1211102 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.8966. Min Act: -0.0000

Data Index: 610416 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.7271. Min Act: -0.0000

Data Index: 548185 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.0161. Min Act: -0.0000

Data Index: 631038 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.7774. Min Act: -0.0000

Data Index: 428704 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.5265. Min Act: -0.0000

Data Index: 785996 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.8675. Min Act: -0.0000

Data Index: 1532172 (Python Code)

Max Activating Token Index: 1011

Text #16

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.7562. Min Act: -0.0000

Data Index: 228955 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.7668. Min Act: -0.0000

Data Index: 411082 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 3.0370. Min Range: -3.0370

Max Act: 2.0390. Min Act: -0.0000

Data Index: 994081 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 3.0370. Min Range: -3.0370

Max Act: 1.6973. Min Act: -0.0000

Data Index: 1194970 (C4 (Web Text))

Max Activating Token Index: 578