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

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

Neuron 4643 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0002

Data Index: 1247692 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5425. Min Act: -0.0002

Data Index: 928241 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5112. Min Act: -0.0002

Data Index: 723877 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5258. Min Act: -0.0002

Data Index: 233615 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5153. Min Act: -0.0003

Data Index: 776978 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4735. Min Act: -0.0002

Data Index: 973810 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4658. Min Act: -0.0003

Data Index: 1242741 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4406. Min Act: -0.0002

Data Index: 725154 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4141. Min Act: -0.0002

Data Index: 904744 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4270. Min Act: -0.0002

Data Index: 1222219 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4218. Min Act: -0.0002

Data Index: 825571 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3987. Min Act: -0.0002

Data Index: 865789 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3957. Min Act: -0.0003

Data Index: 734215 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3811. Min Act: -0.0002

Data Index: 723161 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4175. Min Act: -0.0002

Data Index: 34598 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3894. Min Act: -0.0002

Data Index: 619175 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3696. Min Act: -0.0002

Data Index: 404814 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3547. Min Act: -0.0002

Data Index: 400679 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3278. Min Act: -0.0002

Data Index: 989153 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.3477. Min Act: -0.0003

Data Index: 7409 (C4 (Web Text))

Max Activating Token Index: 45