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

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

Neuron 3425 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6524. Min Act: -0.0001

Data Index: 411702 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6277. Min Act: -0.0002

Data Index: 492332 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6011. Min Act: -0.0001

Data Index: 805042 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5895. Min Act: -0.0001

Data Index: 1647974 (Python Code)

Max Activating Token Index: 562

Text #4

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.6294. Min Act: -0.0002

Data Index: 920513 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5416. Min Act: -0.0001

Data Index: 1389655 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5442. Min Act: -0.0001

Data Index: 1399925 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5378. Min Act: -0.0002

Data Index: 877456 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4934. Min Act: -0.0001

Data Index: 821968 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5294. Min Act: -0.0002

Data Index: 1256265 (C4 (Web Text))

Max Activating Token Index: 421

Text #10

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4912. Min Act: -0.0002

Data Index: 326590 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5244. Min Act: -0.0001

Data Index: 721147 (C4 (Web Text))

Max Activating Token Index: 80

Text #12

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4894. Min Act: -0.0001

Data Index: 1119633 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5517. Min Act: -0.0001

Data Index: 815971 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5524. Min Act: -0.0001

Data Index: 631810 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4774. Min Act: -0.0002

Data Index: 215970 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5138. Min Act: -0.0001

Data Index: 1327842 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.5233. Min Act: -0.0002

Data Index: 448487 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4950. Min Act: -0.0002

Data Index: 634807 (C4 (Web Text))

Max Activating Token Index: 727

Text #19

Max Range: 0.6524. Min Range: -0.6524

Max Act: 0.4921. Min Act: -0.0002

Data Index: 311201 (C4 (Web Text))

Max Activating Token Index: 463