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

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

Neuron 2892 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7784. Min Range: -1.7784

Max Act: 1.7784. Min Act: -0.0000

Data Index: 673586 (C4 (Web Text))

Max Activating Token Index: 668

Text #1

Max Range: 1.7784. Min Range: -1.7784

Max Act: 1.3723. Min Act: -0.0000

Data Index: 765064 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 1.7784. Min Range: -1.7784

Max Act: 1.3873. Min Act: -0.0000

Data Index: 820745 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.7784. Min Range: -1.7784

Max Act: 1.2519. Min Act: -0.0000

Data Index: 1062626 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.7784. Min Range: -1.7784

Max Act: 1.2179. Min Act: -0.0000

Data Index: 738174 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 1.7784. Min Range: -1.7784

Max Act: 1.0826. Min Act: -0.0000

Data Index: 789434 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.8250. Min Act: -0.0000

Data Index: 601963 (C4 (Web Text))

Max Activating Token Index: 829

Text #7

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.8735. Min Act: -0.0000

Data Index: 308542 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.8619. Min Act: -0.0000

Data Index: 1146112 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.7712. Min Act: -0.0000

Data Index: 899707 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.7136. Min Act: -0.0000

Data Index: 924844 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.7143. Min Act: -0.0000

Data Index: 138880 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.7633. Min Act: -0.0000

Data Index: 822877 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1171849 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.6718. Min Act: -0.0000

Data Index: 385545 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.6836. Min Act: -0.0000

Data Index: 466189 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.6670. Min Act: -0.0000

Data Index: 1352966 (C4 (Web Text))

Max Activating Token Index: 110

Text #17

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1075466 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1163094 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 1.7784. Min Range: -1.7784

Max Act: 0.6050. Min Act: -0.0000

Data Index: 647943 (C4 (Web Text))

Max Activating Token Index: 100