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

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

Neuron 4976 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.4019. Min Act: -0.0002

Data Index: 391868 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.2491. Min Act: -0.0002

Data Index: 1031680 (C4 (Web Text))

Max Activating Token Index: 999

Text #2

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.2371. Min Act: -0.0002

Data Index: 907365 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.1832. Min Act: -0.0002

Data Index: 1132240 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0830. Min Act: -0.0002

Data Index: 728351 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0889. Min Act: -0.0002

Data Index: 336377 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0128. Min Act: -0.0002

Data Index: 626236 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0658. Min Act: -0.0002

Data Index: 1282049 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0577. Min Act: -0.0002

Data Index: 319938 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 2.4019. Min Range: -2.4019

Max Act: 1.9470. Min Act: -0.0002

Data Index: 407989 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0892. Min Act: -0.0002

Data Index: 826065 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0552. Min Act: -0.0002

Data Index: 540033 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0883. Min Act: -0.0002

Data Index: 402502 (C4 (Web Text))

Max Activating Token Index: 651

Text #13

Max Range: 2.4019. Min Range: -2.4019

Max Act: 1.9378. Min Act: -0.0002

Data Index: 935553 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 2.4019. Min Range: -2.4019

Max Act: 1.8427. Min Act: -0.0002

Data Index: 1148865 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 2.4019. Min Range: -2.4019

Max Act: 1.8509. Min Act: -0.0002

Data Index: 1318888 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 2.4019. Min Range: -2.4019

Max Act: 1.9134. Min Act: -0.0002

Data Index: 836024 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 2.4019. Min Range: -2.4019

Max Act: 1.8438. Min Act: -0.0002

Data Index: 187956 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 2.4019. Min Range: -2.4019

Max Act: 1.8481. Min Act: -0.0002

Data Index: 1185666 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 2.4019. Min Range: -2.4019

Max Act: 2.0443. Min Act: -0.0002

Data Index: 1065666 (C4 (Web Text))

Max Activating Token Index: 64