Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3303 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.1150. Min Act: -0.0000

Data Index: 811002 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0907. Min Act: -0.0000

Data Index: 63546 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0883. Min Act: -0.0000

Data Index: 369376 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0852. Min Act: -0.0001

Data Index: 79364 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0883. Min Act: -0.0000

Data Index: 1397277 (Python Code)

Max Activating Token Index: 606

Text #5

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0869. Min Act: -0.0000

Data Index: 632280 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0838. Min Act: -0.0000

Data Index: 884489 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0843. Min Act: -0.0001

Data Index: 296143 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0806. Min Act: -0.0000

Data Index: 123986 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1036128 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0773. Min Act: -0.0001

Data Index: 163044 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0748. Min Act: -0.0001

Data Index: 720498 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0798. Min Act: -0.0001

Data Index: 602162 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0768. Min Act: -0.0000

Data Index: 118080 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0770. Min Act: -0.0000

Data Index: 134036 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0739. Min Act: -0.0000

Data Index: 218646 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0735. Min Act: -0.0000

Data Index: 288306 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1176294 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0711. Min Act: -0.0000

Data Index: 998725 (C4 (Web Text))

Max Activating Token Index: 873

Text #19

Max Range: 0.1150. Min Range: -0.1150

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1200181 (C4 (Web Text))

Max Activating Token Index: 40