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

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

Neuron 5381 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.3033. Min Act: -0.0001

Data Index: 566156 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1005361 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.2137. Min Act: -0.0001

Data Index: 1147770 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.1911. Min Act: -0.0001

Data Index: 760892 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1044717 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1039540 (C4 (Web Text))

Max Activating Token Index: 297

Text #6

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1235320 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0641. Min Act: -0.0001

Data Index: 34963 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1477765 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1512525 (Python Code)

Max Activating Token Index: 707

Text #10

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0567. Min Act: -0.0001

Data Index: 700001 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0741. Min Act: -0.0001

Data Index: 1371544 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1414872 (Python Code)

Max Activating Token Index: 580

Text #13

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0577. Min Act: -0.0001

Data Index: 1631583 (Python Code)

Max Activating Token Index: 154

Text #14

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1656928 (Python Code)

Max Activating Token Index: 461

Text #15

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0561. Min Act: -0.0001

Data Index: 1374841 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1546175 (Python Code)

Max Activating Token Index: 489

Text #17

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0528. Min Act: -0.0001

Data Index: 1386278 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0494. Min Act: -0.0001

Data Index: 1105217 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.3073. Min Range: -0.3073

Max Act: 0.0491. Min Act: -0.0001

Data Index: 654638 (C4 (Web Text))

Max Activating Token Index: 546