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

Dataset: The Pile

Neuron 1866 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.7049. Min Range: -9.7049

Max Act: 9.5454. Min Act: -0.0000

Data Index: 513834 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 9.7049. Min Range: -9.7049

Max Act: 9.6330. Min Act: -0.0000

Data Index: 604451 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 9.7049. Min Range: -9.7049

Max Act: 9.7049. Min Act: -0.0000

Data Index: 648052 (The Pile)

Max Activating Token Index: 705

Text #3

Max Range: 9.7049. Min Range: -9.7049

Max Act: 7.6295. Min Act: -0.0000

Data Index: 1642169 (The Pile)

Max Activating Token Index: 267

Text #4

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.8396. Min Act: -0.0000

Data Index: 548600 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.7117. Min Act: -0.0000

Data Index: 1383835 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.5199. Min Act: -0.0000

Data Index: 1432914 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.3526. Min Act: -0.0000

Data Index: 407779 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 9.7049. Min Range: -9.7049

Max Act: 9.1423. Min Act: -0.0000

Data Index: 332705 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.6430. Min Act: -0.0000

Data Index: 461267 (The Pile)

Max Activating Token Index: 809

Text #10

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.6099. Min Act: -0.0000

Data Index: 369805 (The Pile)

Max Activating Token Index: 718

Text #11

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.3066. Min Act: -0.0000

Data Index: 223130 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 9.7049. Min Range: -9.7049

Max Act: 8.4695. Min Act: -0.0000

Data Index: 865025 (The Pile)

Max Activating Token Index: 367

Text #13

Max Range: 9.7049. Min Range: -9.7049

Max Act: 7.8610. Min Act: -0.0000

Data Index: 1787969 (The Pile)

Max Activating Token Index: 542

Text #14

Max Range: 9.7049. Min Range: -9.7049

Max Act: 6.9817. Min Act: -0.0000

Data Index: 1770491 (The Pile)

Max Activating Token Index: 147

Text #15

Max Range: 9.7049. Min Range: -9.7049

Max Act: 7.6896. Min Act: -0.0000

Data Index: 1165510 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 9.7049. Min Range: -9.7049

Max Act: 7.3692. Min Act: -0.0000

Data Index: 304018 (The Pile)

Max Activating Token Index: 461

Text #17

Max Range: 9.7049. Min Range: -9.7049

Max Act: 7.1337. Min Act: -0.0000

Data Index: 890697 (The Pile)

Max Activating Token Index: 784

Text #18

Max Range: 9.7049. Min Range: -9.7049

Max Act: 9.0337. Min Act: -0.0000

Data Index: 859479 (The Pile)

Max Activating Token Index: 649

Text #19

Max Range: 9.7049. Min Range: -9.7049

Max Act: 7.7975. Min Act: -0.0000

Data Index: 1478928 (The Pile)

Max Activating Token Index: 180