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

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

Neuron 4084 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7598. Min Act: -0.0001

Data Index: 624708 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7557. Min Act: -0.0001

Data Index: 527993 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7096. Min Act: -0.0001

Data Index: 1148462 (C4 (Web Text))

Max Activating Token Index: 689

Text #3

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6657. Min Act: -0.0001

Data Index: 96077 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7468. Min Act: -0.0001

Data Index: 874992 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6622. Min Act: -0.0001

Data Index: 1318044 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6421. Min Act: -0.0001

Data Index: 108283 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7337. Min Act: -0.0001

Data Index: 1054270 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6803. Min Act: -0.0001

Data Index: 946459 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7069. Min Act: -0.0001

Data Index: 499871 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7269. Min Act: -0.0001

Data Index: 20004 (C4 (Web Text))

Max Activating Token Index: 933

Text #11

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6703. Min Act: -0.0001

Data Index: 256885 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6546. Min Act: -0.0001

Data Index: 1332294 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7345. Min Act: -0.0001

Data Index: 1241485 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6479. Min Act: -0.0001

Data Index: 1223970 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6637. Min Act: -0.0001

Data Index: 892889 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6760. Min Act: -0.0001

Data Index: 453444 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7199. Min Act: -0.0001

Data Index: 624404 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.6744. Min Act: -0.0001

Data Index: 838713 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.7598. Min Range: -0.7598

Max Act: 0.7263. Min Act: -0.0001

Data Index: 678146 (C4 (Web Text))

Max Activating Token Index: 962