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

Dataset: The Pile

Neuron 2412 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2298. Min Range: -3.2298

Max Act: 3.2298. Min Act: -0.0000

Data Index: 343081 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.5413. Min Act: -0.0000

Data Index: 1182665 (The Pile)

Max Activating Token Index: 620

Text #2

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3882. Min Act: -0.0000

Data Index: 725408 (The Pile)

Max Activating Token Index: 235

Text #3

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.6607. Min Act: -0.0000

Data Index: 117021 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.4629. Min Act: -0.0000

Data Index: 1100554 (The Pile)

Max Activating Token Index: 687

Text #5

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3009. Min Act: -0.0000

Data Index: 898544 (The Pile)

Max Activating Token Index: 233

Text #6

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.1822. Min Act: -0.0000

Data Index: 338490 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.6400. Min Act: -0.0000

Data Index: 1050545 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3726. Min Act: -0.0000

Data Index: 106948 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3936. Min Act: -0.0000

Data Index: 441063 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.2486. Min Act: -0.0000

Data Index: 1450117 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3413. Min Act: -0.0000

Data Index: 1821022 (The Pile)

Max Activating Token Index: 983

Text #12

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.5726. Min Act: -0.0000

Data Index: 209992 (The Pile)

Max Activating Token Index: 921

Text #13

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.1009. Min Act: -0.0000

Data Index: 1155087 (The Pile)

Max Activating Token Index: 807

Text #14

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3159. Min Act: -0.0000

Data Index: 1619745 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.1819. Min Act: -0.0000

Data Index: 1645770 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.0616. Min Act: -0.0000

Data Index: 1866733 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3715. Min Act: -0.0000

Data Index: 1615044 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.1824. Min Act: -0.0000

Data Index: 1461209 (The Pile)

Max Activating Token Index: 351

Text #19

Max Range: 3.2298. Min Range: -3.2298

Max Act: 2.3034. Min Act: -0.0000

Data Index: 1124297 (The Pile)

Max Activating Token Index: 146