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

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

Neuron 1473 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3294. Min Act: -0.0001

Data Index: 620361 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3926. Min Act: -0.0001

Data Index: 680192 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3597. Min Act: -0.0001

Data Index: 874646 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3080. Min Act: -0.0001

Data Index: 769117 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2833. Min Act: -0.0001

Data Index: 486213 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2726. Min Act: -0.0001

Data Index: 1514803 (Python Code)

Max Activating Token Index: 56

Text #6

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3058. Min Act: -0.0001

Data Index: 516015 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3227. Min Act: -0.0001

Data Index: 658671 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.3533. Min Act: -0.0001

Data Index: 963060 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2264. Min Act: -0.0001

Data Index: 1117455 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.1658. Min Act: -0.0001

Data Index: 1113803 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2538. Min Act: -0.0001

Data Index: 303468 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2402. Min Act: -0.0001

Data Index: 935293 (C4 (Web Text))

Max Activating Token Index: 751

Text #13

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.2264. Min Act: -0.0001

Data Index: 331430 (C4 (Web Text))

Max Activating Token Index: 789

Text #14

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0485. Min Act: -0.0001

Data Index: 1381780 (Python Code)

Max Activating Token Index: 98

Text #15

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0487. Min Act: -0.0001

Data Index: 1327862 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0788. Min Act: -0.0001

Data Index: 1076886 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0259. Min Act: -0.0001

Data Index: 1617220 (Python Code)

Max Activating Token Index: 568

Text #18

Max Range: 1.3926. Min Range: -1.3926

Max Act: 1.0559. Min Act: -0.0001

Data Index: 1374849 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 1.3926. Min Range: -1.3926

Max Act: 0.9487. Min Act: -0.0001

Data Index: 514451 (C4 (Web Text))

Max Activating Token Index: 231