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

Dataset: The Pile

Neuron 4565 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.4349. Min Act: -0.0000

Data Index: 326480 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3718. Min Act: -0.0000

Data Index: 501140 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1435731 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3396. Min Act: -0.0000

Data Index: 25629 (The Pile)

Max Activating Token Index: 337

Text #4

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3382. Min Act: -0.0000

Data Index: 745310 (The Pile)

Max Activating Token Index: 353

Text #5

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3213. Min Act: -0.0000

Data Index: 1330856 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3414. Min Act: -0.0000

Data Index: 25211 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3028. Min Act: -0.0000

Data Index: 1957724 (The Pile)

Max Activating Token Index: 398

Text #8

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3050. Min Act: -0.0000

Data Index: 108349 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3007. Min Act: -0.0000

Data Index: 398536 (The Pile)

Max Activating Token Index: 213

Text #10

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1116647 (The Pile)

Max Activating Token Index: 582

Text #11

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2837. Min Act: -0.0000

Data Index: 543306 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2983. Min Act: -0.0000

Data Index: 660757 (The Pile)

Max Activating Token Index: 802

Text #13

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2970. Min Act: -0.0000

Data Index: 935284 (The Pile)

Max Activating Token Index: 254

Text #14

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1625578 (The Pile)

Max Activating Token Index: 727

Text #15

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2846. Min Act: -0.0000

Data Index: 234509 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1760102 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2754. Min Act: -0.0000

Data Index: 371281 (The Pile)

Max Activating Token Index: 825

Text #18

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2858. Min Act: -0.0000

Data Index: 1789553 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.4349. Min Range: -0.4349

Max Act: 0.2830. Min Act: -0.0000

Data Index: 918328 (The Pile)

Max Activating Token Index: 257