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

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

Neuron 1877 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2736. Min Range: -3.2736

Max Act: 3.2736. Min Act: -0.0000

Data Index: 917315 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.5087. Min Act: -0.0000

Data Index: 1154977 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.4355. Min Act: -0.0000

Data Index: 926484 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.4245. Min Act: -0.0000

Data Index: 268117 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.5056. Min Act: -0.0001

Data Index: 926748 (C4 (Web Text))

Max Activating Token Index: 96

Text #5

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.5666. Min Act: -0.0000

Data Index: 1032420 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.3211. Min Act: -0.0000

Data Index: 1102412 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.2693. Min Act: -0.0000

Data Index: 666031 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.1975. Min Act: -0.0000

Data Index: 885129 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 3.2736. Min Range: -3.2736

Max Act: 1.8513. Min Act: -0.0000

Data Index: 318970 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.0086. Min Act: -0.0000

Data Index: 155527 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.2109. Min Act: -0.0000

Data Index: 587614 (C4 (Web Text))

Max Activating Token Index: 943

Text #12

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.0032. Min Act: -0.0000

Data Index: 1325002 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 3.2736. Min Range: -3.2736

Max Act: 1.9838. Min Act: -0.0000

Data Index: 771238 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 3.2736. Min Range: -3.2736

Max Act: 1.9195. Min Act: -0.0000

Data Index: 209016 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.0188. Min Act: -0.0000

Data Index: 309100 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 3.2736. Min Range: -3.2736

Max Act: 2.0528. Min Act: -0.0000

Data Index: 46718 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 3.2736. Min Range: -3.2736

Max Act: 1.9520. Min Act: -0.0000

Data Index: 835314 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 3.2736. Min Range: -3.2736

Max Act: 1.8436. Min Act: -0.0000

Data Index: 260969 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 3.2736. Min Range: -3.2736

Max Act: 1.8262. Min Act: -0.0000

Data Index: 441444 (C4 (Web Text))

Max Activating Token Index: 736