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

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

Neuron 5001 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: 1.2971. Min Range: -1.2971

Max Act: 1.2971. Min Act: -0.0001

Data Index: 258914 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1725. Min Act: -0.0001

Data Index: 1109036 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.1036. Min Act: -0.0001

Data Index: 1322408 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0715. Min Act: -0.0000

Data Index: 1078978 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0781. Min Act: -0.0001

Data Index: 1427894 (Python Code)

Max Activating Token Index: 518

Text #5

Max Range: 1.2971. Min Range: -1.2971

Max Act: 1.0135. Min Act: -0.0001

Data Index: 1195641 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9657. Min Act: -0.0001

Data Index: 229578 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9838. Min Act: -0.0001

Data Index: 773143 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9261. Min Act: -0.0001

Data Index: 429004 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8839. Min Act: -0.0001

Data Index: 162116 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9993. Min Act: -0.0001

Data Index: 594625 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.9196. Min Act: -0.0001

Data Index: 272697 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8820. Min Act: -0.0001

Data Index: 748458 (C4 (Web Text))

Max Activating Token Index: 640

Text #13

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8534. Min Act: -0.0001

Data Index: 770204 (C4 (Web Text))

Max Activating Token Index: 275

Text #14

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8311. Min Act: -0.0001

Data Index: 1621495 (Python Code)

Max Activating Token Index: 215

Text #15

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8761. Min Act: -0.0001

Data Index: 806388 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8378. Min Act: -0.0001

Data Index: 209073 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8335. Min Act: -0.0001

Data Index: 359246 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8791. Min Act: -0.0001

Data Index: 204925 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 1.2971. Min Range: -1.2971

Max Act: 0.8232. Min Act: -0.0001

Data Index: 1606953 (Python Code)

Max Activating Token Index: 523