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

Dataset: The Pile

Neuron 4273 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: 1.3406. Min Range: -1.3406

Max Act: 1.3399. Min Act: -0.0000

Data Index: 547039 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1005315 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.2189. Min Act: -0.0000

Data Index: 1180466 (The Pile)

Max Activating Token Index: 962

Text #3

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1670978 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0899. Min Act: -0.0000

Data Index: 1231162 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.9690. Min Act: -0.0000

Data Index: 586909 (The Pile)

Max Activating Token Index: 570

Text #6

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1590294 (The Pile)

Max Activating Token Index: 1011

Text #7

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0702. Min Act: -0.0000

Data Index: 771154 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0461. Min Act: -0.0000

Data Index: 28282 (The Pile)

Max Activating Token Index: 435

Text #9

Max Range: 1.3406. Min Range: -1.3406

Max Act: 1.0697. Min Act: -0.0000

Data Index: 428488 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1348763 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.8998. Min Act: -0.0000

Data Index: 1874140 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1537286 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.9760. Min Act: -0.0000

Data Index: 732593 (The Pile)

Max Activating Token Index: 172

Text #14

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1325812 (The Pile)

Max Activating Token Index: 348

Text #15

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.8842. Min Act: -0.0000

Data Index: 847690 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.9409. Min Act: -0.0000

Data Index: 530215 (The Pile)

Max Activating Token Index: 425

Text #17

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.8937. Min Act: -0.0000

Data Index: 998183 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.8546. Min Act: -0.0000

Data Index: 261248 (The Pile)

Max Activating Token Index: 680

Text #19

Max Range: 1.3406. Min Range: -1.3406

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1614029 (The Pile)

Max Activating Token Index: 1014