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

Dataset: The Pile

Neuron 5002 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: 9.5278. Min Range: -9.5278

Max Act: 9.4894. Min Act: -0.0000

Data Index: 1759194 (The Pile)

Max Activating Token Index: 286

Text #1

Max Range: 9.5278. Min Range: -9.5278

Max Act: 9.5278. Min Act: -0.0000

Data Index: 470764 (The Pile)

Max Activating Token Index: 276

Text #2

Max Range: 9.5278. Min Range: -9.5278

Max Act: 9.2348. Min Act: -0.0000

Data Index: 62493 (The Pile)

Max Activating Token Index: 277

Text #3

Max Range: 9.5278. Min Range: -9.5278

Max Act: 9.3965. Min Act: -0.0000

Data Index: 938228 (The Pile)

Max Activating Token Index: 353

Text #4

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.9684. Min Act: -0.0000

Data Index: 161695 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 9.5278. Min Range: -9.5278

Max Act: 9.1060. Min Act: -0.0000

Data Index: 1719800 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.9945. Min Act: -0.0000

Data Index: 1366808 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.7348. Min Act: -0.0000

Data Index: 311834 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.7319. Min Act: -0.0000

Data Index: 713337 (The Pile)

Max Activating Token Index: 589

Text #9

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.8107. Min Act: -0.0000

Data Index: 1902077 (The Pile)

Max Activating Token Index: 423

Text #10

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.5966. Min Act: -0.0000

Data Index: 1512777 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.5441. Min Act: -0.0000

Data Index: 1712417 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.5289. Min Act: -0.0000

Data Index: 674677 (The Pile)

Max Activating Token Index: 235

Text #13

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.3430. Min Act: -0.0000

Data Index: 874102 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.5933. Min Act: -0.0000

Data Index: 1149826 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.4539. Min Act: -0.0000

Data Index: 1227649 (The Pile)

Max Activating Token Index: 130

Text #16

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.6827. Min Act: -0.0000

Data Index: 602091 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.3507. Min Act: -0.0000

Data Index: 521969 (The Pile)

Max Activating Token Index: 641

Text #18

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.6407. Min Act: -0.0000

Data Index: 1908746 (The Pile)

Max Activating Token Index: 453

Text #19

Max Range: 9.5278. Min Range: -9.5278

Max Act: 8.4526. Min Act: -0.0000

Data Index: 601728 (The Pile)

Max Activating Token Index: 313