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

Dataset: The Pile

Neuron 5109 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: 3.6005. Min Range: -3.6005

Max Act: 3.4266. Min Act: -0.0000

Data Index: 1408432 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.6005. Min Act: -0.0000

Data Index: 41394 (The Pile)

Max Activating Token Index: 1019

Text #2

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.8002. Min Act: -0.0000

Data Index: 1585620 (The Pile)

Max Activating Token Index: 811

Text #3

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.8101. Min Act: -0.0000

Data Index: 1927037 (The Pile)

Max Activating Token Index: 997

Text #4

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.1487. Min Act: -0.0000

Data Index: 828884 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.2131. Min Act: -0.0000

Data Index: 1839396 (The Pile)

Max Activating Token Index: 445

Text #6

Max Range: 3.6005. Min Range: -3.6005

Max Act: 3.0497. Min Act: -0.0000

Data Index: 1322168 (The Pile)

Max Activating Token Index: 874

Text #7

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.9665. Min Act: -0.0000

Data Index: 1502632 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.7388. Min Act: -0.0000

Data Index: 1085353 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.9235. Min Act: -0.0000

Data Index: 1289087 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.7531. Min Act: -0.0000

Data Index: 1218146 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.8246. Min Act: -0.0000

Data Index: 1360137 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.8271. Min Act: -0.0000

Data Index: 56204 (The Pile)

Max Activating Token Index: 402

Text #13

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.8536. Min Act: -0.0000

Data Index: 1134274 (The Pile)

Max Activating Token Index: 194

Text #14

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.3736. Min Act: -0.0000

Data Index: 768993 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.6836. Min Act: -0.0000

Data Index: 1569534 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.6302. Min Act: -0.0000

Data Index: 1023748 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.7339. Min Act: -0.0000

Data Index: 1084044 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.4516. Min Act: -0.0000

Data Index: 1104566 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 3.6005. Min Range: -3.6005

Max Act: 2.3472. Min Act: -0.0000

Data Index: 766475 (The Pile)

Max Activating Token Index: 738