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

Dataset: The Pile

Neuron 4540 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.2683. Min Act: -0.0000

Data Index: 744191 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.2781. Min Act: -0.0000

Data Index: 12951 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.4763. Min Act: -0.0000

Data Index: 1012622 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.1856. Min Act: -0.0000

Data Index: 1577464 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 3.2781. Min Range: -3.2781

Max Act: 3.2199. Min Act: -0.0000

Data Index: 305935 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.7976. Min Act: -0.0000

Data Index: 289715 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.7659. Min Act: -0.0000

Data Index: 1802008 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.6444. Min Act: -0.0000

Data Index: 539353 (The Pile)

Max Activating Token Index: 333

Text #8

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.5075. Min Act: -0.0000

Data Index: 910979 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.5828. Min Act: -0.0000

Data Index: 1972267 (The Pile)

Max Activating Token Index: 245

Text #10

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.7176. Min Act: -0.0000

Data Index: 1621541 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.3140. Min Act: -0.0000

Data Index: 425149 (The Pile)

Max Activating Token Index: 867

Text #12

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.5602. Min Act: -0.0000

Data Index: 1785368 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.5313. Min Act: -0.0000

Data Index: 1103318 (The Pile)

Max Activating Token Index: 305

Text #14

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.6916. Min Act: -0.0000

Data Index: 1672399 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.3748. Min Act: -0.0000

Data Index: 1389076 (The Pile)

Max Activating Token Index: 364

Text #16

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.3997. Min Act: -0.0000

Data Index: 626715 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.6171. Min Act: -0.0000

Data Index: 1567415 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.4811. Min Act: -0.0000

Data Index: 655097 (The Pile)

Max Activating Token Index: 425

Text #19

Max Range: 3.2781. Min Range: -3.2781

Max Act: 2.2443. Min Act: -0.0000

Data Index: 1898284 (The Pile)

Max Activating Token Index: 72