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

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

Neuron 3514 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: 0.6813. Min Range: -0.6813

Max Act: 0.6813. Min Act: -0.0001

Data Index: 246654 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5066. Min Act: -0.0001

Data Index: 357385 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.5032. Min Act: -0.0000

Data Index: 699955 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4904. Min Act: -0.0000

Data Index: 222802 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4719. Min Act: -0.0001

Data Index: 375763 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4447. Min Act: -0.0000

Data Index: 832123 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4614. Min Act: -0.0001

Data Index: 1294909 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4747. Min Act: -0.0001

Data Index: 254865 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4571. Min Act: -0.0001

Data Index: 853202 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4541. Min Act: -0.0001

Data Index: 1118837 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4537. Min Act: -0.0000

Data Index: 415183 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4262. Min Act: -0.0000

Data Index: 564916 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1350905 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4486. Min Act: -0.0000

Data Index: 1243605 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4054. Min Act: -0.0000

Data Index: 698153 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4045. Min Act: -0.0000

Data Index: 322564 (C4 (Web Text))

Max Activating Token Index: 557

Text #16

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.4024. Min Act: -0.0001

Data Index: 702935 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.3977. Min Act: -0.0000

Data Index: 1097624 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.3921. Min Act: -0.0000

Data Index: 565 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.6813. Min Range: -0.6813

Max Act: 0.3920. Min Act: -0.0001

Data Index: 718303 (C4 (Web Text))

Max Activating Token Index: 688