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

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

Neuron 4072 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: 4.4825. Min Range: -4.4825

Max Act: 4.4825. Min Act: -0.0000

Data Index: 969277 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 4.4825. Min Range: -4.4825

Max Act: 4.0672. Min Act: -0.0000

Data Index: 1835 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 4.4825. Min Range: -4.4825

Max Act: 4.0131. Min Act: -0.0000

Data Index: 789017 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 4.4825. Min Range: -4.4825

Max Act: 3.4956. Min Act: -0.0000

Data Index: 1076917 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 4.4825. Min Range: -4.4825

Max Act: 3.4694. Min Act: -0.0000

Data Index: 478673 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 4.4825. Min Range: -4.4825

Max Act: 3.1271. Min Act: -0.0000

Data Index: 816065 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 4.4825. Min Range: -4.4825

Max Act: 3.3757. Min Act: -0.0000

Data Index: 298782 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 4.4825. Min Range: -4.4825

Max Act: 3.4462. Min Act: -0.0000

Data Index: 705414 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.9327. Min Act: -0.0000

Data Index: 329500 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.8739. Min Act: -0.0000

Data Index: 616787 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 4.4825. Min Range: -4.4825

Max Act: 3.0350. Min Act: -0.0000

Data Index: 1529973 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.8470. Min Act: -0.0000

Data Index: 1073974 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.8286. Min Act: -0.0000

Data Index: 532727 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.8116. Min Act: -0.0000

Data Index: 1146794 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.6519. Min Act: -0.0000

Data Index: 1147003 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.7451. Min Act: -0.0000

Data Index: 912137 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.8546. Min Act: -0.0000

Data Index: 884596 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.7089. Min Act: -0.0000

Data Index: 263460 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.5747. Min Act: -0.0000

Data Index: 593380 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 4.4825. Min Range: -4.4825

Max Act: 2.8328. Min Act: -0.0000

Data Index: 1137207 (C4 (Web Text))

Max Activating Token Index: 608