Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2670 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.5213. Min Act: -0.0000

Data Index: 879303 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.7246. Min Act: -0.0000

Data Index: 905160 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.7632. Min Act: -0.0000

Data Index: 1028057 (The Pile)

Max Activating Token Index: 841

Text #3

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.1404. Min Act: -0.0000

Data Index: 1968264 (The Pile)

Max Activating Token Index: 330

Text #4

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.3240. Min Act: -0.0000

Data Index: 1730658 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.4498. Min Act: -0.0000

Data Index: 603988 (The Pile)

Max Activating Token Index: 728

Text #6

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.3316. Min Act: -0.0000

Data Index: 1477426 (The Pile)

Max Activating Token Index: 676

Text #7

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.2778. Min Act: -0.0000

Data Index: 565650 (The Pile)

Max Activating Token Index: 433

Text #8

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.8021. Min Act: -0.0000

Data Index: 152335 (The Pile)

Max Activating Token Index: 994

Text #9

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.8241. Min Act: -0.0000

Data Index: 1390456 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 3.7632. Min Range: -3.7632

Max Act: 3.1999. Min Act: -0.0000

Data Index: 1741535 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.4748. Min Act: -0.0000

Data Index: 479557 (The Pile)

Max Activating Token Index: 486

Text #12

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.7057. Min Act: -0.0000

Data Index: 62322 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.6893. Min Act: -0.0000

Data Index: 1605853 (The Pile)

Max Activating Token Index: 611

Text #14

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.8150. Min Act: -0.0000

Data Index: 499162 (The Pile)

Max Activating Token Index: 412

Text #15

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.7899. Min Act: -0.0000

Data Index: 896737 (The Pile)

Max Activating Token Index: 483

Text #16

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.9666. Min Act: -0.0000

Data Index: 835640 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.7404. Min Act: -0.0000

Data Index: 1549478 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.7935. Min Act: -0.0000

Data Index: 400831 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 3.7632. Min Range: -3.7632

Max Act: 2.7804. Min Act: -0.0000

Data Index: 470273 (The Pile)

Max Activating Token Index: 151