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

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

Neuron 4427 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: 3.3073. Min Range: -3.3073

Max Act: 3.3073. Min Act: -0.0000

Data Index: 30952 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.2206. Min Act: -0.0000

Data Index: 1014421 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.2893. Min Act: -0.0000

Data Index: 1309353 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.3407. Min Act: -0.0000

Data Index: 872080 (C4 (Web Text))

Max Activating Token Index: 249

Text #4

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.1926. Min Act: -0.0000

Data Index: 997418 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.1764. Min Act: -0.0000

Data Index: 1172303 (C4 (Web Text))

Max Activating Token Index: 323

Text #6

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.1713. Min Act: -0.0000

Data Index: 241335 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.1597. Min Act: -0.0000

Data Index: 1328068 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.2674. Min Act: -0.0000

Data Index: 926715 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.1151. Min Act: -0.0000

Data Index: 1103197 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.0648. Min Act: -0.0000

Data Index: 722902 (C4 (Web Text))

Max Activating Token Index: 825

Text #11

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.0424. Min Act: -0.0000

Data Index: 469590 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.0270. Min Act: -0.0000

Data Index: 584324 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.0027. Min Act: -0.0000

Data Index: 165648 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 3.3073. Min Range: -3.3073

Max Act: 1.9914. Min Act: -0.0000

Data Index: 91638 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 3.3073. Min Range: -3.3073

Max Act: 1.9587. Min Act: -0.0000

Data Index: 729646 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 3.3073. Min Range: -3.3073

Max Act: 1.9450. Min Act: -0.0000

Data Index: 852462 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 3.3073. Min Range: -3.3073

Max Act: 1.8461. Min Act: -0.0000

Data Index: 60262 (C4 (Web Text))

Max Activating Token Index: 727

Text #18

Max Range: 3.3073. Min Range: -3.3073

Max Act: 1.9155. Min Act: -0.0000

Data Index: 1343499 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 3.3073. Min Range: -3.3073

Max Act: 2.0082. Min Act: -0.0000

Data Index: 885939 (C4 (Web Text))

Max Activating Token Index: 119