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

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

Neuron 1058 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.6554. Min Act: -0.0000

Data Index: 413395 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.7245. Min Act: -0.0000

Data Index: 810627 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.5097. Min Act: -0.0000

Data Index: 227959 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.5531. Min Act: -0.0001

Data Index: 1154511 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.4532. Min Act: -0.0001

Data Index: 574333 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.5307. Min Act: -0.0001

Data Index: 253064 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.5141. Min Act: -0.0000

Data Index: 443882 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.5383. Min Act: -0.0001

Data Index: 384650 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.5932. Min Act: -0.0001

Data Index: 791045 (C4 (Web Text))

Max Activating Token Index: 820

Text #9

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.3088. Min Act: -0.0001

Data Index: 445172 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.4706. Min Act: -0.0000

Data Index: 358857 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.4538. Min Act: -0.0001

Data Index: 1104144 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.4354. Min Act: -0.0001

Data Index: 906594 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.4430. Min Act: -0.0001

Data Index: 987051 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.3642. Min Act: -0.0001

Data Index: 627185 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.3002. Min Act: -0.0001

Data Index: 1210153 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.3620. Min Act: -0.0001

Data Index: 171062 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.2504. Min Act: -0.0001

Data Index: 814558 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.3448. Min Act: -0.0000

Data Index: 412040 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 1.7245. Min Range: -1.7245

Max Act: 1.2668. Min Act: -0.0000

Data Index: 840005 (C4 (Web Text))

Max Activating Token Index: 713