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

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

Neuron 3070 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: 1.9004. Min Range: -1.9004

Max Act: 1.9004. Min Act: -0.0000

Data Index: 88267 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.6469. Min Act: -0.0000

Data Index: 195804 (C4 (Web Text))

Max Activating Token Index: 276

Text #2

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.5820. Min Act: -0.0000

Data Index: 562661 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.5130. Min Act: -0.0000

Data Index: 147910 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.5284. Min Act: -0.0000

Data Index: 1348283 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.4118. Min Act: -0.0000

Data Index: 477468 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.4944. Min Act: -0.0000

Data Index: 661682 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.6650. Min Act: -0.0000

Data Index: 719040 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1308898 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.3794. Min Act: -0.0000

Data Index: 583398 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.6172. Min Act: -0.0000

Data Index: 278093 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.3653. Min Act: -0.0000

Data Index: 56158 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.5245. Min Act: -0.0000

Data Index: 821902 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.0779. Min Act: -0.0000

Data Index: 452266 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.3264. Min Act: -0.0000

Data Index: 503465 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.3952. Min Act: -0.0000

Data Index: 52450 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.4754. Min Act: -0.0000

Data Index: 123289 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.2681. Min Act: -0.0000

Data Index: 1022187 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.4292. Min Act: -0.0000

Data Index: 1048444 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 1.9004. Min Range: -1.9004

Max Act: 1.3658. Min Act: -0.0000

Data Index: 538826 (C4 (Web Text))

Max Activating Token Index: 634