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

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

Neuron 2206 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.6656. Min Act: -0.0000

Data Index: 165687 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4725. Min Act: 0.0001

Data Index: 624629 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4981. Min Act: -0.0000

Data Index: 489548 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4957. Min Act: -0.0000

Data Index: 472092 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4736. Min Act: -0.0000

Data Index: 773111 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4575. Min Act: -0.0000

Data Index: 579922 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4706. Min Act: 0.0000

Data Index: 1043022 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1233864 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4622. Min Act: 0.0000

Data Index: 123417 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4446. Min Act: -0.0000

Data Index: 653448 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4628. Min Act: -0.0000

Data Index: 821925 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4573. Min Act: -0.0000

Data Index: 19275 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4537. Min Act: 0.0000

Data Index: 602664 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4440. Min Act: -0.0000

Data Index: 982710 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4683. Min Act: -0.0000

Data Index: 596839 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4060. Min Act: -0.0000

Data Index: 979750 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4244. Min Act: 0.0000

Data Index: 473869 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4236. Min Act: -0.0000

Data Index: 613272 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4062. Min Act: -0.0000

Data Index: 287029 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.6656. Min Range: -0.6656

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1058222 (C4 (Web Text))

Max Activating Token Index: 473