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

Dataset: The Pile

Neuron 4405 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.7940. Min Act: -0.0000

Data Index: 1343011 (The Pile)

Max Activating Token Index: 722

Text #1

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1341159 (The Pile)

Max Activating Token Index: 580

Text #2

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1278959 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1900541 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6037. Min Act: -0.0000

Data Index: 525403 (The Pile)

Max Activating Token Index: 651

Text #5

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.6247. Min Act: 0.0000

Data Index: 1801558 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1126666 (The Pile)

Max Activating Token Index: 924

Text #7

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5986. Min Act: -0.0000

Data Index: 10836 (The Pile)

Max Activating Token Index: 287

Text #8

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5921. Min Act: -0.0000

Data Index: 137777 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1750708 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1231942 (The Pile)

Max Activating Token Index: 90

Text #11

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5594. Min Act: 0.0000

Data Index: 1959828 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5713. Min Act: 0.0000

Data Index: 268076 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5369. Min Act: -0.0000

Data Index: 689758 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5468. Min Act: -0.0000

Data Index: 426919 (The Pile)

Max Activating Token Index: 397

Text #15

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5269. Min Act: -0.0000

Data Index: 439054 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5437. Min Act: 0.0000

Data Index: 1855950 (The Pile)

Max Activating Token Index: 608

Text #17

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1920831 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1178785 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 0.7940. Min Range: -0.7940

Max Act: 0.4969. Min Act: 0.0001

Data Index: 243361 (The Pile)

Max Activating Token Index: 189