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

Dataset: The Pile

Neuron 1193 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: 0.8991. Min Range: -0.8991

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1624465 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8991. Min Act: -0.0000

Data Index: 952978 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7793. Min Act: -0.0000

Data Index: 972793 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1230081 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1258800 (The Pile)

Max Activating Token Index: 119

Text #5

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8622. Min Act: -0.0000

Data Index: 986882 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.8656. Min Act: 0.0000

Data Index: 1800863 (The Pile)

Max Activating Token Index: 713

Text #7

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1558474 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1365880 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1888768 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1993915 (The Pile)

Max Activating Token Index: 953

Text #11

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7554. Min Act: -0.0000

Data Index: 262714 (The Pile)

Max Activating Token Index: 916

Text #12

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1561231 (The Pile)

Max Activating Token Index: 937

Text #13

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.7044. Min Act: -0.0000

Data Index: 86503 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6532. Min Act: -0.0000

Data Index: 728020 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6560. Min Act: -0.0000

Data Index: 792272 (The Pile)

Max Activating Token Index: 427

Text #16

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6093. Min Act: 0.0000

Data Index: 1877288 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6068. Min Act: 0.0000

Data Index: 1650557 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1922364 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 0.8991. Min Range: -0.8991

Max Act: 0.6428. Min Act: 0.0000

Data Index: 1294029 (The Pile)

Max Activating Token Index: 102