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

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

Neuron 1548 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0561. Min Range: -5.0561

Max Act: 5.0561. Min Act: -0.0000

Data Index: 1026018 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 5.0561. Min Range: -5.0561

Max Act: 4.2321. Min Act: -0.0000

Data Index: 998997 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 5.0561. Min Range: -5.0561

Max Act: 4.1573. Min Act: -0.0000

Data Index: 653242 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.5448. Min Act: -0.0000

Data Index: 125951 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.4905. Min Act: -0.0000

Data Index: 508432 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.3502. Min Act: -0.0000

Data Index: 129702 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.4574. Min Act: -0.0000

Data Index: 284772 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.4642. Min Act: -0.0000

Data Index: 1205426 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.4619. Min Act: -0.0000

Data Index: 1253478 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.6152. Min Act: -0.0000

Data Index: 477822 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.2468. Min Act: -0.0000

Data Index: 133938 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.5067. Min Act: -0.0000

Data Index: 301151 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.0553. Min Act: -0.0000

Data Index: 994515 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.2990. Min Act: -0.0000

Data Index: 695306 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.1637. Min Act: -0.0000

Data Index: 703232 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.1097. Min Act: -0.0000

Data Index: 1160702 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 5.0561. Min Range: -5.0561

Max Act: 2.9286. Min Act: -0.0000

Data Index: 1019863 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.2240. Min Act: -0.0000

Data Index: 979456 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 5.0561. Min Range: -5.0561

Max Act: 2.7652. Min Act: -0.0000

Data Index: 404236 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 5.0561. Min Range: -5.0561

Max Act: 3.1837. Min Act: -0.0000

Data Index: 297430 (C4 (Web Text))

Max Activating Token Index: 26